It also supports full local agent if you have a GPU with 25GB RAM which enables realtime conversation along with tool calling.
I started this as a hobby project last year when I started exploring voice agents and every saw every Saas tried to lock you in their eco system. Since then project has taken off and a lot of asterisk people started using it due to ease of setup and wide range of providers and flexibility.
Core is MIT: https://github.com/hkjarral/AVA-AI-Voice-Agent-for-Asterisk\nFree and open source forever.
No install Mock UI us hosted at: https://demo.agent6789.com
I am also exploring to convert this into a more polished version for Operators to handle multiple customer and multi tenant environment and I would genuinely like to hear feedback on it.
Happy to answer any questions and gather any feedback. Thanks."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Self-hosted voice AI agent for Asterisk/FreePBX"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ai"],"value":"https://github.com/hkjarral/AVA-AI-Voice-Agent-for-Asterisk"}},"_tags":["story","author_hkjarral","story_48887276","show_hn"],"author":"hkjarral","children":[48887300,48890269,48910587,48913507,48913688,48913699,48913723,48915163,48921504,49017880],"created_at":"2026-07-13T02:51:34Z","created_at_i":1783911094,"num_comments":11,"objectID":"48887276","points":32,"story_id":48887276,"story_text":"Hi HN folks ! I am the author of AVA, a self hosted AI Voice Agent that plugs into Asterisk/Freepbx so you own all the aspects of an AI Voice agent in your own infrastructure. \nIt uses Asterisk native Audiosocket/RTP with python engine to run STT,LLM and TTS loop. The project support several full providers openai, gemini, grok, elevenlabs out of the box and also provides options to build custom pipelines by choosing different stt tts and llm.
It also supports full local agent if you have a GPU with 25GB RAM which enables realtime conversation along with tool calling.
I started this as a hobby project last year when I started exploring voice agents and every saw every Saas tried to lock you in their eco system. Since then project has taken off and a lot of asterisk people started using it due to ease of setup and wide range of providers and flexibility.
Core is MIT: https://github.com/hkjarral/AVA-AI-Voice-Agent-for-Asterisk\nFree and open source forever.
No install Mock UI us hosted at: https://demo.agent6789.com
I am also exploring to convert this into a more polished version for Operators to handle multiple customer and multi tenant environment and I would genuinely like to hear feedback on it.
Happy to answer any questions and gather any feedback. Thanks.","title":"Show HN: Self-hosted voice AI agent for Asterisk/FreePBX","updated_at":"2026-07-26T07:27:13Z","url":"https://github.com/hkjarral/AVA-AI-Voice-Agent-for-Asterisk"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"gkamer8"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Abbey: Self-hosted AI interface server for documents, notebooks, and chats"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/US-Artificial-Intelligence/abbey"}},"_tags":["story","author_gkamer8","story_42186467"],"author":"gkamer8","children":[42186502,42186663,42193363],"created_at":"2024-11-19T18:11:59Z","created_at_i":1732039919,"num_comments":5,"objectID":"42186467","points":32,"story_id":42186467,"title":"Abbey: Self-hosted AI interface server for documents, notebooks, and chats","updated_at":"2024-11-24T21:13:42Z","url":"https://github.com/US-Artificial-Intelligence/abbey"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"csmajorfive"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Startup School Afterparty hosted by AirBnB"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ai"],"value":"http://blog.airbnb.com/airbnb-y-combinator-present-a-party-of-epic-p"}},"_tags":["story","author_csmajorfive","story_1758520"],"author":"csmajorfive","children":[1758723],"created_at":"2010-10-05T03:46:32Z","created_at_i":1286250392,"num_comments":6,"objectID":"1758520","points":25,"story_id":1758520,"title":"Startup School Afterparty hosted by AirBnB","updated_at":"2024-09-19T17:14:51Z","url":"http://blog.airbnb.com/airbnb-y-combinator-present-a-party-of-epic-p"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"janober"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Self-Hosted AI Starter Kit"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"https://github.com/n8n-io/self-hosted-ai-starter-kit"}},"_tags":["story","author_janober","story_41313223","show_hn"],"author":"janober","children":[41318060],"created_at":"2024-08-21T19:10:31Z","created_at_i":1724267431,"num_comments":1,"objectID":"41313223","points":21,"story_id":41313223,"title":"Show HN: Self-Hosted AI Starter Kit","updated_at":"2025-02-24T03:13:26Z","url":"https://github.com/n8n-io/self-hosted-ai-starter-kit"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"upmostly"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Hey HN,
I'm Jay, co-creator of Mira. An open-source, self-hosted AI code reviewer where you BYOK (bring your own key).
Local models are getting really good.
Hosted frontier models are getting really expensive.
So, we built Mira. Mira has some snazzy features too:
- It's really fast at reviewing. Average is 77s compared with Greptile's 5 minutes. Your PRs aren't going into a queue on a cloud somewhere.
- Mira performs a blast radius and see what damage will be done with code change.
- Learns your codebase's patterns from the repo itself and enforces them without a config file.
- It's self-hosted, so your code never leaves your infrastructure. Bring your own model - OpenAI, Anthropic, or a local LLM behind your firewall.
We're really active, and looking for active contributors. Come join us in our discord!
https://github.com/miracodeai/mira
Thanks,\nJay"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Mira \u2013 Open-source and self-hosted AI code reviewer"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/miracodeai/mira"}},"_tags":["story","author_upmostly","story_48570197","show_hn"],"author":"upmostly","children":[48570562],"created_at":"2026-06-17T13:23:54Z","created_at_i":1781702634,"num_comments":2,"objectID":"48570197","points":15,"story_id":48570197,"story_text":"Hey HN,
I'm Jay, co-creator of Mira. An open-source, self-hosted AI code reviewer where you BYOK (bring your own key).
Local models are getting really good.
Hosted frontier models are getting really expensive.
So, we built Mira. Mira has some snazzy features too:
- It's really fast at reviewing. Average is 77s compared with Greptile's 5 minutes. Your PRs aren't going into a queue on a cloud somewhere.
- Mira performs a blast radius and see what damage will be done with code change.
- Learns your codebase's patterns from the repo itself and enforces them without a config file.
- It's self-hosted, so your code never leaves your infrastructure. Bring your own model - OpenAI, Anthropic, or a local LLM behind your firewall.
We're really active, and looking for active contributors. Come join us in our discord!
https://github.com/miracodeai/mira
Thanks,\nJay","title":"Show HN: Mira \u2013 Open-source and self-hosted AI code reviewer","updated_at":"2026-06-18T14:07:41Z","url":"https://github.com/miracodeai/mira"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"CharlesW"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Hugging Face, the GitHub of AI, hosted code that backdoored user devices"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"https://arstechnica.com/security/2024/03/hugging-face-the-github-of-ai-hosted-code-that-backdoored-user-devices/"}},"_tags":["story","author_CharlesW","story_39569656"],"author":"CharlesW","children":[39569918,39569977],"created_at":"2024-03-02T03:54:54Z","created_at_i":1709351694,"num_comments":0,"objectID":"39569656","points":15,"story_id":39569656,"title":"Hugging Face, the GitHub of AI, hosted code that backdoored user devices","updated_at":"2024-09-20T16:32:04Z","url":"https://arstechnica.com/security/2024/03/hugging-face-the-github-of-ai-hosted-code-that-backdoored-user-devices/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"bram2w"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Baserow \u2013 Self Hosted Airtable Alternative Launches No-Code Application Builder"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://baserow.io/blog/1-23-release-of-baserow"}},"_tags":["story","author_bram2w","story_39690588"],"author":"bram2w","children":[39690660],"created_at":"2024-03-13T12:30:21Z","created_at_i":1710333021,"num_comments":1,"objectID":"39690588","points":14,"story_id":39690588,"title":"Baserow \u2013 Self Hosted Airtable Alternative Launches No-Code Application Builder","updated_at":"2024-09-20T16:41:47Z","url":"https://baserow.io/blog/1-23-release-of-baserow"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mythz"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Self Hosted AI Server Gateway for Ollama, ComfyUI and FFmpeg Servers"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://openai.servicestack.net"}},"_tags":["story","author_mythz","story_42327801","show_hn"],"author":"mythz","created_at":"2024-12-05T13:01:22Z","created_at_i":1733403682,"num_comments":0,"objectID":"42327801","points":13,"story_id":42327801,"title":"Show HN: Self Hosted AI Server Gateway for Ollama, ComfyUI and FFmpeg Servers","updated_at":"2024-12-07T13:15:12Z","url":"https://openai.servicestack.net"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"jterenzio"},"story_text":{"matchLevel":"none","matchedWords":[],"value":""},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"SDK Mindset \u2013 A Braintree Tech Talk Hosted by Airbnb \u2013 11/5"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ai"],"value":"https://www.airbnb.com/meetups/fmjb2q4c9-sdk-mindset"}},"_tags":["story","author_jterenzio","story_8551873"],"author":"jterenzio","created_at":"2014-11-03T17:01:08Z","created_at_i":1415034068,"num_comments":0,"objectID":"8551873","points":12,"story_id":8551873,"story_text":"","title":"SDK Mindset \u2013 A Braintree Tech Talk Hosted by Airbnb \u2013 11/5","updated_at":"2024-09-19T21:17:50Z","url":"https://www.airbnb.com/meetups/fmjb2q4c9-sdk-mindset"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"exasol_nerd"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Self-hosted AI data workflow: DB and Ollama and SQL"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ai"],"value":"https://exasol.github.io/developer-documentation/main/gen_ai/ai_text_summary/index.html"}},"_tags":["story","author_exasol_nerd","story_46708002"],"author":"exasol_nerd","children":[46708004],"created_at":"2026-01-21T16:36:26Z","created_at_i":1769013386,"num_comments":3,"objectID":"46708002","points":11,"story_id":46708002,"title":"Self-hosted AI data workflow: DB and Ollama and SQL","updated_at":"2026-03-05T23:22:34Z","url":"https://exasol.github.io/developer-documentation/main/gen_ai/ai_text_summary/index.html"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"suveen_ellawela"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Open-source self-hosted AI voice interviewer platform for Hiring"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/FoloUp/FoloUp"}},"_tags":["story","author_suveen_ellawela","story_42988651","show_hn"],"author":"suveen_ellawela","children":[42989676,42997462],"created_at":"2025-02-09T05:15:26Z","created_at_i":1739078126,"num_comments":5,"objectID":"42988651","points":10,"story_id":42988651,"title":"Show HN: Open-source self-hosted AI voice interviewer platform for Hiring","updated_at":"2025-02-15T05:48:50Z","url":"https://github.com/FoloUp/FoloUp"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"nateb2022"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Amazon Lightsail now offers OpenClaw, a private self-hosted AI assistant"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://aws.amazon.com/about-aws/whats-new/2026/03/amazon-lightsail-openclaw/"}},"_tags":["story","author_nateb2022","story_47265828"],"author":"nateb2022","created_at":"2026-03-05T19:06:49Z","created_at_i":1772737609,"num_comments":0,"objectID":"47265828","points":8,"story_id":47265828,"title":"Amazon Lightsail now offers OpenClaw, a private self-hosted AI assistant","updated_at":"2026-03-06T15:21:59Z","url":"https://aws.amazon.com/about-aws/whats-new/2026/03/amazon-lightsail-openclaw/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ethantheswe"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"I've been building a bunch of random side projects, as I'm sure we all are. Most analytics tools were either too heavy or required juggling multiple free tiers across different subdomains.
After looking what's out there I couldn't find a lightweight analytics platform that worked on the free tier of fly.io.
It's a single Go binary using DuckDB for events and SQLite for metadata, so there are no external dependencies to manage. Drop a script tag on your site and it auto-captures pageviews and clicks.
The part I'm most excited about: it uses an LLM to automatically name raw click events into something human-readable. Instead of seeing button.btn-primary#checkout in your dashboard, you see "Clicked checkout button". No manual event instrumentation needed.
One fly launch and you have your own analytics instance for free.
GitHub: https://github.com/danielthedm/clicknest"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: ClickNest a tiny self-hosted, AI native web analytics in Go"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/danielthedm/clicknest"}},"_tags":["story","author_ethantheswe","story_47172751","show_hn"],"author":"ethantheswe","children":[47176062,47183033],"created_at":"2026-02-26T22:15:38Z","created_at_i":1772144138,"num_comments":1,"objectID":"47172751","points":6,"story_id":47172751,"story_text":"I've been building a bunch of random side projects, as I'm sure we all are. Most analytics tools were either too heavy or required juggling multiple free tiers across different subdomains.
After looking what's out there I couldn't find a lightweight analytics platform that worked on the free tier of fly.io.
It's a single Go binary using DuckDB for events and SQLite for metadata, so there are no external dependencies to manage. Drop a script tag on your site and it auto-captures pageviews and clicks.
The part I'm most excited about: it uses an LLM to automatically name raw click events into something human-readable. Instead of seeing button.btn-primary#checkout in your dashboard, you see "Clicked checkout button". No manual event instrumentation needed.
One fly launch and you have your own analytics instance for free.
GitHub: https://github.com/danielthedm/clicknest","title":"Show HN: ClickNest a tiny self-hosted, AI native web analytics in Go","updated_at":"2026-03-30T18:57:07Z","url":"https://github.com/danielthedm/clicknest"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"dvictor"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"Eliezer is ~7K lines of TypeScript, MIT open-source
- PWA for mobile/desktop with push notifications \n- Self-editing protocol \n- Builds and displays interactive apps/widgets right in the chat \n- Task and Crons - "notify if sunny tomorrow at 10am") \n- Persistent SQLite memory + auto context compaction\n- Bring your own LLM API key (Kimi/Claude/Grok/etc.) \n- Full visibility/control - You see all tool calls and can abort in all states
Agent repo: https://github.com/Eliezer-app/eliezer\nChat repo: https://github.com/Eliezer-app/clawchat
The chat was originally thought as a plugin for OpenClaw.\nEnded up writing the agent too."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Eliezer \u2013 Tiny (~7K LOC) Self-Hosted AI Agent (PWA, Self-Editing)"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.eliezer.app/"}},"_tags":["story","author_dvictor","story_47102479","show_hn"],"author":"dvictor","children":[47102550],"created_at":"2026-02-21T17:00:23Z","created_at_i":1771693223,"num_comments":1,"objectID":"47102479","points":6,"story_id":47102479,"story_text":"Eliezer is ~7K lines of TypeScript, MIT open-source
- PWA for mobile/desktop with push notifications \n- Self-editing protocol \n- Builds and displays interactive apps/widgets right in the chat \n- Task and Crons - "notify if sunny tomorrow at 10am") \n- Persistent SQLite memory + auto context compaction\n- Bring your own LLM API key (Kimi/Claude/Grok/etc.) \n- Full visibility/control - You see all tool calls and can abort in all states
Agent repo: https://github.com/Eliezer-app/eliezer\nChat repo: https://github.com/Eliezer-app/clawchat
The chat was originally thought as a plugin for OpenClaw.\nEnded up writing the agent too.","title":"Show HN: Eliezer \u2013 Tiny (~7K LOC) Self-Hosted AI Agent (PWA, Self-Editing)","updated_at":"2026-03-05T23:34:13Z","url":"https://www.eliezer.app/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"yuvalsteuer"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: self-hosted, AI-powered search engine for your workplace"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/GerevAI/gerev"}},"_tags":["story","author_yuvalsteuer","story_35262739","show_hn"],"author":"yuvalsteuer","children":[35262740],"created_at":"2023-03-22T15:38:12Z","created_at_i":1679499492,"num_comments":1,"objectID":"35262739","points":6,"story_id":35262739,"title":"Show HN: self-hosted, AI-powered search engine for your workplace","updated_at":"2024-09-20T13:39:45Z","url":"https://github.com/GerevAI/gerev"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"SencerH"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Hi everyone,
I read HN every day, but there was always more great content than I had time to read.
I know there are already several HN summarizers on GitHub, and I tried some of them. They just didn't fit the workflow I wanted, so I decided to build my own.
My project is a self-hosted app that automatically fetches top stories, summarizes them with AI, translates them into your preferred language, and prepares a personalized daily briefing in a nice customizable UI while you sleep.
Maybe I'm not the only one who wanted this kind of workflow.
I'd love to hear your thoughts, especially on what you think an ideal HN summarizer should do."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: A self-hosted AI that turns Hacker News into a daily briefing"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ai"],"value":"https://github.com/RecNes/hn-ai-summarizer"}},"_tags":["story","author_SencerH","story_48972350","show_hn"],"author":"SencerH","created_at":"2026-07-19T22:40:57Z","created_at_i":1784500857,"num_comments":0,"objectID":"48972350","points":5,"story_id":48972350,"story_text":"Hi everyone,
I read HN every day, but there was always more great content than I had time to read.
I know there are already several HN summarizers on GitHub, and I tried some of them. They just didn't fit the workflow I wanted, so I decided to build my own.
My project is a self-hosted app that automatically fetches top stories, summarizes them with AI, translates them into your preferred language, and prepares a personalized daily briefing in a nice customizable UI while you sleep.
Maybe I'm not the only one who wanted this kind of workflow.
I'd love to hear your thoughts, especially on what you think an ideal HN summarizer should do.","title":"Show HN: A self-hosted AI that turns Hacker News into a daily briefing","updated_at":"2026-07-20T07:30:52Z","url":"https://github.com/RecNes/hn-ai-summarizer"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"rntn"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Reg attends job interview hosted by AI avatar, struggles to exit uncanny valley"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ai"],"value":"https://www.theregister.com/2025/09/06/ai_job_interview_experience/"}},"_tags":["story","author_rntn","story_45149345"],"author":"rntn","created_at":"2025-09-06T14:03:21Z","created_at_i":1757167401,"num_comments":0,"objectID":"45149345","points":5,"story_id":45149345,"title":"Reg attends job interview hosted by AI avatar, struggles to exit uncanny valley","updated_at":"2026-03-05T22:39:57Z","url":"https://www.theregister.com/2025/09/06/ai_job_interview_experience/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"deevus"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"PewDiePie using self-hosted AI"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.youtube.com/watch?v=qw4fDU18RcU"}},"_tags":["story","author_deevus","story_45778656"],"author":"deevus","children":[45778675,45778732],"created_at":"2025-11-01T01:57:55Z","created_at_i":1761962275,"num_comments":2,"objectID":"45778656","points":4,"story_id":45778656,"title":"PewDiePie using self-hosted AI","updated_at":"2026-03-05T22:59:40Z","url":"https://www.youtube.com/watch?v=qw4fDU18RcU"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Bender"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Reg hack attends job interview hosted by AI avatar struggles exit uncanny valley"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ai"],"value":"https://www.theregister.com/2025/09/06/ai_job_interview_experience/"}},"_tags":["story","author_Bender","story_45163102"],"author":"Bender","children":[45163177,45163348],"created_at":"2025-09-07T23:19:11Z","created_at_i":1757287151,"num_comments":2,"objectID":"45163102","points":4,"story_id":45163102,"title":"Reg hack attends job interview hosted by AI avatar struggles exit uncanny valley","updated_at":"2026-03-05T22:40:50Z","url":"https://www.theregister.com/2025/09/06/ai_job_interview_experience/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"nateb2022"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"OpenReview: Open-source, self-hosted AI code review bot powered by Vercel"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/vercel-labs/openreview"}},"_tags":["story","author_nateb2022","story_47413785"],"author":"nateb2022","children":[47413812,47413952],"created_at":"2026-03-17T15:10:14Z","created_at_i":1773760214,"num_comments":1,"objectID":"47413785","points":4,"story_id":47413785,"title":"OpenReview: Open-source, self-hosted AI code review bot powered by Vercel","updated_at":"2026-05-11T09:38:57Z","url":"https://github.com/vercel-labs/openreview"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Alrady"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Self-Hosted AI That Sees, Plays Minecraft, and Reacts"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/Alradyin/wallie-V2"}},"_tags":["story","author_Alrady","story_48843648","show_hn"],"author":"Alrady","created_at":"2026-07-09T10:29:27Z","created_at_i":1783592967,"num_comments":0,"objectID":"48843648","points":4,"story_id":48843648,"title":"Show HN: Self-Hosted AI That Sees, Plays Minecraft, and Reacts","updated_at":"2026-07-09T17:01:20Z","url":"https://github.com/Alradyin/wallie-V2"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"debankad"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: AgentArk \u2013 open-source self-hosted AI agent OS"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ai"],"value":"https://github.com/agentark-ai/AgentArk"}},"_tags":["story","author_debankad","story_48606186","show_hn"],"author":"debankad","children":[48606189,48606196],"created_at":"2026-06-20T03:45:06Z","created_at_i":1781927106,"num_comments":0,"objectID":"48606186","points":4,"story_id":48606186,"title":"Show HN: AgentArk \u2013 open-source self-hosted AI agent OS","updated_at":"2026-06-21T18:09:53Z","url":"https://github.com/agentark-ai/AgentArk"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"syncerx"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Frona v2026.5.5 \u2013 self-hosted personal AI assistant"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/fronalabs/frona/releases/tag/v2026.5.5"}},"_tags":["story","author_syncerx","story_48340093"],"author":"syncerx","children":[48340094],"created_at":"2026-05-30T20:03:54Z","created_at_i":1780171434,"num_comments":0,"objectID":"48340093","points":4,"story_id":48340093,"title":"Frona v2026.5.5 \u2013 self-hosted personal AI assistant","updated_at":"2026-05-31T07:59:01Z","url":"https://github.com/fronalabs/frona/releases/tag/v2026.5.5"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"zhendershot"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"We built CongaLine to solve a specific problem: give teams and individuals self-hosted AI assistants without collapsing everyone into a shared instance. Each agent runs in its own Docker container with isolated networks, secrets, and config. Security is the primary design constraint.
Three deployment targets via a single Go CLI (conga):
- Local: Docker Desktop, no cloud required \n - Remote: any SSH-accessible Linux host (VPS, Raspberry Pi, bare metal)\n - AWS: zero-ingress via SSM, no inbound ports\nChannels are optional. Every agent gets a web UI via SSH/SSM tunnel. Slack and Telegram are both supported, each with a dedicated router container that fans events to per-agent containers. Two agent types: user agents (DM-based) and team agents (channel-based).
The name is literal: spiny lobsters travel in single-file conga lines during seasonal migration, in physical contact, reducing drag and sharing protection. A procession of isolated-but-coordinated agents.
Apache 2.0. Repo has Terraform for AWS, a Go CLI, and a Node.js Slack router.
Would love feedback on the provider abstraction. We're planning Kubernetes and GCP next."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: CongaLine \u2013 Self-hosted isolated AI agent fleet (OpenClaw, Hermes)"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/cruxdigital-llc/congaline"}},"_tags":["story","author_zhendershot","story_47696273","show_hn"],"author":"zhendershot","children":[47701715,47716010],"created_at":"2026-04-08T21:06:35Z","created_at_i":1775682395,"num_comments":0,"objectID":"47696273","points":4,"story_id":47696273,"story_text":"We built CongaLine to solve a specific problem: give teams and individuals self-hosted AI assistants without collapsing everyone into a shared instance. Each agent runs in its own Docker container with isolated networks, secrets, and config. Security is the primary design constraint.
Three deployment targets via a single Go CLI (conga):
- Local: Docker Desktop, no cloud required \n - Remote: any SSH-accessible Linux host (VPS, Raspberry Pi, bare metal)\n - AWS: zero-ingress via SSM, no inbound ports\nChannels are optional. Every agent gets a web UI via SSH/SSM tunnel. Slack and Telegram are both supported, each with a dedicated router container that fans events to per-agent containers. Two agent types: user agents (DM-based) and team agents (channel-based).
The name is literal: spiny lobsters travel in single-file conga lines during seasonal migration, in physical contact, reducing drag and sharing protection. A procession of isolated-but-coordinated agents.
Apache 2.0. Repo has Terraform for AWS, a Go CLI, and a Node.js Slack router.
Would love feedback on the provider abstraction. We're planning Kubernetes and GCP next.","title":"Show HN: CongaLine \u2013 Self-hosted isolated AI agent fleet (OpenClaw, Hermes)","updated_at":"2026-04-17T02:13:46Z","url":"https://github.com/cruxdigital-llc/congaline"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"syncerx"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Frona \u2013 self-hosted personal AI assistant"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/fronalabs/frona"}},"_tags":["story","author_syncerx","story_47655176"],"author":"syncerx","children":[47655177],"created_at":"2026-04-05T23:47:09Z","created_at_i":1775432829,"num_comments":0,"objectID":"47655176","points":4,"story_id":47655176,"title":"Frona \u2013 self-hosted personal AI assistant","updated_at":"2026-04-06T03:06:32Z","url":"https://github.com/fronalabs/frona"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"t_peersky"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"Hey HN,\nWe're open-sourcing (source-available, BSL 1.1, patent pending) the orchestrator behind our paper benchmark results. NSED (N-Way Self-Evaluating Deliberation) is a Rust binary that coordinates multiple LLMs through structured rounds of proposals and cross-evaluation, using quadratic voting to prevent any single model from dominating the consensus.
The result: Three open-weight models (20B, 8B, 12B) on consumer GPUs \u2014 64GB total VRAM, ~$7K hardware \u2014 score 84% on AIME 2025. The same models individually or with naive majority voting score ~54%. That's frontier-model performance on hardware you can buy at Micro Center.
How it works:
Each agent independently proposes a solution\nEvery agent evaluates every other agent's work\nScores aggregate via quadratic voting (cost of influence grows quadratically \u2192 no single model can dominate)\nRepeat. Agents see prior results, refine, re-evaluate\nSystem converges toward the highest-quality answer through adversarial cross-checking
It's provider-agnostic \u2014 mix Ollama, vLLM, OpenAI, Anthropic, or any OpenAI-compatible endpoint in the same deliberation. Everything streams over NATS JetStream with full persistence: every proposal, evaluation, score, and reasoning trace is logged and streamable via SSE.
Paper: arxiv.org/abs/2601.16863\nHappy to answer questions about the architecture, the quadratic voting mechanism, benchmark methodology, or anything else."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: NSED is public \u2013 Mixture-of-Models to Hit SOTA using self-hosted AI"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/peeramid-labs/nsed"}},"_tags":["story","author_t_peersky","story_47067772","show_hn"],"author":"t_peersky","created_at":"2026-02-18T23:21:15Z","created_at_i":1771456875,"num_comments":0,"objectID":"47067772","points":4,"story_id":47067772,"story_text":"Hey HN,\nWe're open-sourcing (source-available, BSL 1.1, patent pending) the orchestrator behind our paper benchmark results. NSED (N-Way Self-Evaluating Deliberation) is a Rust binary that coordinates multiple LLMs through structured rounds of proposals and cross-evaluation, using quadratic voting to prevent any single model from dominating the consensus.
The result: Three open-weight models (20B, 8B, 12B) on consumer GPUs \u2014 64GB total VRAM, ~$7K hardware \u2014 score 84% on AIME 2025. The same models individually or with naive majority voting score ~54%. That's frontier-model performance on hardware you can buy at Micro Center.
How it works:
Each agent independently proposes a solution\nEvery agent evaluates every other agent's work\nScores aggregate via quadratic voting (cost of influence grows quadratically \u2192 no single model can dominate)\nRepeat. Agents see prior results, refine, re-evaluate\nSystem converges toward the highest-quality answer through adversarial cross-checking
It's provider-agnostic \u2014 mix Ollama, vLLM, OpenAI, Anthropic, or any OpenAI-compatible endpoint in the same deliberation. Everything streams over NATS JetStream with full persistence: every proposal, evaluation, score, and reasoning trace is logged and streamable via SSE.
Paper: arxiv.org/abs/2601.16863\nHappy to answer questions about the architecture, the quadratic voting mechanism, benchmark methodology, or anything else.","title":"Show HN: NSED is public \u2013 Mixture-of-Models to Hit SOTA using self-hosted AI","updated_at":"2026-03-05T23:35:25Z","url":"https://github.com/peeramid-labs/nsed"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"beeeph"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: My AI-Hosted YouTube Channel for Teaching Apple XR Development"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.youtube.com/@swiftreality"}},"_tags":["story","author_beeeph","story_34573938","show_hn"],"author":"beeeph","created_at":"2023-01-29T23:30:50Z","created_at_i":1675035050,"num_comments":0,"objectID":"34573938","points":4,"story_id":34573938,"title":"Show HN: My AI-Hosted YouTube Channel for Teaching Apple XR Development","updated_at":"2024-09-20T13:15:18Z","url":"https://www.youtube.com/@swiftreality"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"RedsonNgwira"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Sonder \u2013 self-hosted AI social simulation engine"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/RedsonNgwira/sonder"}},"_tags":["story","author_RedsonNgwira","story_47420182","show_hn"],"author":"RedsonNgwira","children":[47420401,47420763,47421698,47422045],"created_at":"2026-03-18T00:21:40Z","created_at_i":1773793300,"num_comments":4,"objectID":"47420182","points":3,"story_id":47420182,"title":"Show HN: Sonder \u2013 self-hosted AI social simulation engine","updated_at":"2026-04-06T06:58:48Z","url":"https://github.com/RedsonNgwira/sonder"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"heliosnova"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Nova\u2013Self-hosted personal AI learns from corrections &fine-tunes itself"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/HeliosNova/nova"}},"_tags":["story","author_heliosnova","story_47393086","show_hn"],"author":"heliosnova","children":[47393087],"created_at":"2026-03-15T23:18:18Z","created_at_i":1773616698,"num_comments":3,"objectID":"47393086","points":3,"story_id":47393086,"title":"Show HN: Nova\u2013Self-hosted personal AI learns from corrections &fine-tunes itself","updated_at":"2026-06-14T06:53:55Z","url":"https://github.com/HeliosNova/nova"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"heimdallr"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"I've been thinking about the privacy tradeoffs when using frontier AI models like Claude or chatgpt.
Even with a VPN, providers still see prompts, and usage is tied to accounts and payment methods linked to identity in some way.
I've been trying to find a way to access these models without creating provider-specific accounts tied to my identity. Ideally, through some kind of intermediary that abstracts identity and doesn't retain prompts.
From a technical and economic perspective, would that kind of setup meaningfully improve privacy, or does it just shift trust? Is meaningful privacy with hosted AI fundamentally unrealistic regardless of architecture?"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Ask HN: Is meaningful privacy possible with hosted AI models?"}},"_tags":["story","author_heimdallr","story_47159175","ask_hn"],"author":"heimdallr","children":[47159283,47159293,47160562,47169746],"created_at":"2026-02-25T22:49:59Z","created_at_i":1772059799,"num_comments":3,"objectID":"47159175","points":3,"story_id":47159175,"story_text":"I've been thinking about the privacy tradeoffs when using frontier AI models like Claude or chatgpt.
Even with a VPN, providers still see prompts, and usage is tied to accounts and payment methods linked to identity in some way.
I've been trying to find a way to access these models without creating provider-specific accounts tied to my identity. Ideally, through some kind of intermediary that abstracts identity and doesn't retain prompts.
From a technical and economic perspective, would that kind of setup meaningfully improve privacy, or does it just shift trust? Is meaningful privacy with hosted AI fundamentally unrealistic regardless of architecture?","title":"Ask HN: Is meaningful privacy possible with hosted AI models?","updated_at":"2026-03-05T23:37:28Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"zozo123-IB"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Run a self-hosted AI workspace on a throwaway cloud box in one command"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://zozo123.github.io/odysseus-crabbox-demo/"}},"_tags":["story","author_zozo123-IB","story_48385150"],"author":"zozo123-IB","children":[48385311],"created_at":"2026-06-03T15:08:33Z","created_at_i":1780499313,"num_comments":2,"objectID":"48385150","points":3,"story_id":48385150,"title":"Run a self-hosted AI workspace on a throwaway cloud box in one command","updated_at":"2026-06-03T16:48:57Z","url":"https://zozo123.github.io/odysseus-crabbox-demo/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"bram2w"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Baserow 2.0: Self-Hosted Airtable Alternative Now Has AI Agents and Automations"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/baserow/baserow"}},"_tags":["story","author_bram2w","story_45967758"],"author":"bram2w","children":[45967759],"created_at":"2025-11-18T15:44:22Z","created_at_i":1763480662,"num_comments":2,"objectID":"45967758","points":3,"story_id":45967758,"title":"Baserow 2.0: Self-Hosted Airtable Alternative Now Has AI Agents and Automations","updated_at":"2026-03-05T23:02:10Z","url":"https://github.com/baserow/baserow"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"patethegreat"},"story_text":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["hosted"],"value":"Hey everyone, we\u2019re excited to announce Jay, a platform for building voice agents that hosts all of the agent\u2019s infra while giving you full control over how the agent responds. Our goal is to give developers a Vercel-like experience for building voice agents.
Currently, voice frameworks are either fully hosted with limited customizability (e.g. Vapi, Retell), or fully customizable while requiring you to host and scale the agent yourself (Livekit, Pipecat). We weren\u2019t satisfied with these options, so we built Jay.
Jay makes it easy for you to add custom logic such as a RAG pipeline, an arbitrary LLM provider, or anything else that controls the LLM\u2019s response. It\u2019s built on top of the standard STT \u2192 LLM \u2192 TTS pipeline, and handles things like voice interruptions automatically. It also supports function calling (i.e. tool calls).
You can deploy your first agent to production in just a few minutes.
Try it out here, and let us know what you think! https://jay.so/"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Jay - Fully programmable, fully hosted AI voice agents"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.jay.so/"}},"_tags":["story","author_patethegreat","story_42857980","show_hn"],"author":"patethegreat","children":[42861906,42865583],"created_at":"2025-01-28T21:04:43Z","created_at_i":1738098283,"num_comments":2,"objectID":"42857980","points":3,"story_id":42857980,"story_text":"Hey everyone, we\u2019re excited to announce Jay, a platform for building voice agents that hosts all of the agent\u2019s infra while giving you full control over how the agent responds. Our goal is to give developers a Vercel-like experience for building voice agents.
Currently, voice frameworks are either fully hosted with limited customizability (e.g. Vapi, Retell), or fully customizable while requiring you to host and scale the agent yourself (Livekit, Pipecat). We weren\u2019t satisfied with these options, so we built Jay.
Jay makes it easy for you to add custom logic such as a RAG pipeline, an arbitrary LLM provider, or anything else that controls the LLM\u2019s response. It\u2019s built on top of the standard STT \u2192 LLM \u2192 TTS pipeline, and handles things like voice interruptions automatically. It also supports function calling (i.e. tool calls).
You can deploy your first agent to production in just a few minutes.
Try it out here, and let us know what you think! https://jay.so/","title":"Show HN: Jay - Fully programmable, fully hosted AI voice agents","updated_at":"2025-03-04T00:46:28Z","url":"https://www.jay.so/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"vsolina"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Today I've made an anticomplex re-implementation of backend for Tabby - self-hosted AI coding assistant.\n(seems fully functional, but some issues are expected)
motivation: I had to move the one I use to another server, but did not want to re-install the entire toolchain and all dependencies.
additionally I like simple stuff which I can understand"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Tabby back end in 20 Python lines (self-hosted AI coding assistant)"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/vsolina/tabby-backend-py"}},"_tags":["story","author_vsolina","story_39181762","show_hn"],"author":"vsolina","children":[39188165],"created_at":"2024-01-29T20:07:56Z","created_at_i":1706558876,"num_comments":2,"objectID":"39181762","points":3,"story_id":39181762,"story_text":"Today I've made an anticomplex re-implementation of backend for Tabby - self-hosted AI coding assistant.\n(seems fully functional, but some issues are expected)
motivation: I had to move the one I use to another server, but did not want to re-install the entire toolchain and all dependencies.
additionally I like simple stuff which I can understand","title":"Show HN: Tabby back end in 20 Python lines (self-hosted AI coding assistant)","updated_at":"2024-09-20T16:18:20Z","url":"https://github.com/vsolina/tabby-backend-py"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"theshrike79"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Odysseys \u2013 A Self-Hosted AI Workspace"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://pewdiepie-archdaemon.github.io/odysseus/"}},"_tags":["story","author_theshrike79","story_48361357"],"author":"theshrike79","children":[48361603],"created_at":"2026-06-01T19:19:32Z","created_at_i":1780341572,"num_comments":1,"objectID":"48361357","points":3,"story_id":48361357,"title":"Odysseys \u2013 A Self-Hosted AI Workspace","updated_at":"2026-06-01T21:20:19Z","url":"https://pewdiepie-archdaemon.github.io/odysseus/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"vitchenkokir"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"GrillKit \u2013 Self-hosted AI trainer for technical interviews with voice"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/GrillKit/grillkit"}},"_tags":["story","author_vitchenkokir","story_48347525"],"author":"vitchenkokir","children":[48347526,48353108],"created_at":"2026-05-31T17:21:19Z","created_at_i":1780248079,"num_comments":1,"objectID":"48347525","points":3,"story_id":48347525,"title":"GrillKit \u2013 Self-hosted AI trainer for technical interviews with voice","updated_at":"2026-06-01T10:13:50Z","url":"https://github.com/GrillKit/grillkit"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"veronica_nigro"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"We are building an open-source library of hosted AI agents and tools that developers can integrate into their graph frameworks with a simple SDK or API call, speeding up development and deployment times. They can use them as-is, customize them for their specific use cases, and even contribute their own agents \u2014 unlocking monetization opportunities."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Mkinf \u2013 an open-source library of hosted AI agents and tools"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://hub.mkinf.io"}},"_tags":["story","author_veronica_nigro","story_43027618","show_hn"],"author":"veronica_nigro","children":[43031827],"created_at":"2025-02-12T17:36:33Z","created_at_i":1739381793,"num_comments":1,"objectID":"43027618","points":3,"story_id":43027618,"story_text":"We are building an open-source library of hosted AI agents and tools that developers can integrate into their graph frameworks with a simple SDK or API call, speeding up development and deployment times. They can use them as-is, customize them for their specific use cases, and even contribute their own agents \u2014 unlocking monetization opportunities.","title":"Show HN: Mkinf \u2013 an open-source library of hosted AI agents and tools","updated_at":"2025-02-13T08:22:42Z","url":"https://hub.mkinf.io"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"fabio2"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Democr.ai \u2013 self-hosted agentic AI runtime with audit and RBAC"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ai"],"value":"https://github.com/democr-ai/democrai"}},"_tags":["story","author_fabio2","story_48935704","show_hn"],"author":"fabio2","children":[48935711,48952896],"created_at":"2026-07-16T15:13:52Z","created_at_i":1784214832,"num_comments":0,"objectID":"48935704","points":3,"story_id":48935704,"title":"Show HN: Democr.ai \u2013 self-hosted agentic AI runtime with audit and RBAC","updated_at":"2026-07-17T22:30:15Z","url":"https://github.com/democr-ai/democrai"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Diwadoo"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"Hey HN,
I wasn't happy with the code review tools we use at work and on my side projects. Noisy, reviews in surface, expensive (overkill for sides). \nSo since Gemini was getting sunsetted, I explored having my own.
As I am a cheap rat, this weekend I built Themis, that works with my Codex/Claude subscriptions (I understood "claude -p" is ok again in subscriptions).
I wanted it open-source so it can help other indie devs or small teams, self-hostable (or local), drawing from subs and mostly, configurable so it works well with your own repos.
No big ambitions nor 1 billion startup here, just fun (so please don't roast ahah). If it is useful to even a few people, that's already great.
Happy to have feedback (especially on distributing the app!)
Ps: 1st HN contrib, hope it's the right format"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Themis \u2013 Self-hosted AI code reviews with your own keys and models"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/Zaimwa9/themis"}},"_tags":["story","author_Diwadoo","story_48903007","show_hn"],"author":"Diwadoo","created_at":"2026-07-14T06:34:22Z","created_at_i":1784010862,"num_comments":0,"objectID":"48903007","points":3,"story_id":48903007,"story_text":"Hey HN,
I wasn't happy with the code review tools we use at work and on my side projects. Noisy, reviews in surface, expensive (overkill for sides). \nSo since Gemini was getting sunsetted, I explored having my own.
As I am a cheap rat, this weekend I built Themis, that works with my Codex/Claude subscriptions (I understood "claude -p" is ok again in subscriptions).
I wanted it open-source so it can help other indie devs or small teams, self-hostable (or local), drawing from subs and mostly, configurable so it works well with your own repos.
No big ambitions nor 1 billion startup here, just fun (so please don't roast ahah). If it is useful to even a few people, that's already great.
Happy to have feedback (especially on distributing the app!)
Ps: 1st HN contrib, hope it's the right format","title":"Show HN: Themis \u2013 Self-hosted AI code reviews with your own keys and models","updated_at":"2026-07-14T11:41:17Z","url":"https://github.com/Zaimwa9/themis"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"SkilfulFox"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: GreyFox \u2013 Free self-hosted AI proxy, token quotas, and local cache"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/skillful-fox-studio/grey-fox-community"}},"_tags":["story","author_SkilfulFox","story_48621680","show_hn"],"author":"SkilfulFox","children":[48621681],"created_at":"2026-06-21T19:09:52Z","created_at_i":1782068992,"num_comments":0,"objectID":"48621680","points":3,"story_id":48621680,"title":"Show HN: GreyFox \u2013 Free self-hosted AI proxy, token quotas, and local cache","updated_at":"2026-06-22T02:30:53Z","url":"https://github.com/skillful-fox-studio/grey-fox-community"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"deepscalelabs"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: Vilvona AI \u2013 Self-Hosted AI Assistant with Tamil and Hindi UI"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ai"],"value":"https://github.com/vignesh2027/Vilvona-AI"}},"_tags":["story","author_deepscalelabs","story_48507644","show_hn"],"author":"deepscalelabs","created_at":"2026-06-12T18:26:24Z","created_at_i":1781288784,"num_comments":0,"objectID":"48507644","points":3,"story_id":48507644,"title":"Show HN: Vilvona AI \u2013 Self-Hosted AI Assistant with Tamil and Hindi UI","updated_at":"2026-06-12T19:31:20Z","url":"https://github.com/vignesh2027/Vilvona-AI"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"masterpos"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Show HN: TetherDust \u2013 Self-hosted AI Analytics Engineer (open source)"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/mpospirit-apps/TetherDust"}},"_tags":["story","author_masterpos","story_48504836","show_hn"],"author":"masterpos","created_at":"2026-06-12T14:43:27Z","created_at_i":1781275407,"num_comments":0,"objectID":"48504836","points":3,"story_id":48504836,"title":"Show HN: TetherDust \u2013 Self-hosted AI Analytics Engineer (open source)","updated_at":"2026-06-14T12:40:56Z","url":"https://github.com/mpospirit-apps/TetherDust"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"sebakubisz"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"TaxHacker \u2013 Self-hosted AI accounting app"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/vas3k/TaxHacker"}},"_tags":["story","author_sebakubisz","story_47864413"],"author":"sebakubisz","created_at":"2026-04-22T14:45:53Z","created_at_i":1776869153,"num_comments":0,"objectID":"47864413","points":3,"story_id":47864413,"title":"TaxHacker \u2013 Self-hosted AI accounting app","updated_at":"2026-04-24T17:51:46Z","url":"https://github.com/vas3k/TaxHacker"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"indigodaddy"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"LibreChat is a self-hosted AI chat platform that unifies all major AI providers"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/danny-avila/LibreChat"}},"_tags":["story","author_indigodaddy","story_47521338"],"author":"indigodaddy","created_at":"2026-03-25T18:31:48Z","created_at_i":1774463508,"num_comments":0,"objectID":"47521338","points":3,"story_id":47521338,"title":"LibreChat is a self-hosted AI chat platform that unifies all major AI providers","updated_at":"2026-03-25T23:41:18Z","url":"https://github.com/danny-avila/LibreChat"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"godsboy7777"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"RepoKeeper \u2013 self-hosted AI agent that triages GitHub issues in 2 seconds"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/GodsBoy/repokeeper"}},"_tags":["story","author_godsboy7777","story_47335154"],"author":"godsboy7777","created_at":"2026-03-11T13:14:50Z","created_at_i":1773234890,"num_comments":0,"objectID":"47335154","points":3,"story_id":47335154,"title":"RepoKeeper \u2013 self-hosted AI agent that triages GitHub issues in 2 seconds","updated_at":"2026-03-15T13:55:02Z","url":"https://github.com/GodsBoy/repokeeper"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"jamescollinssp"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["hosted","ai"],"value":"Building a self-hosted, fast AI research agent using OpenAI and SerpApi"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["hosted"],"value":"https://serpapi.com/blog/building-a-fast-self-hosted-research-agent-with-openai-models-serpapi/"}},"_tags":["story","author_jamescollinssp","story_44950084"],"author":"jamescollinssp","created_at":"2025-08-19T10:30:49Z","created_at_i":1755599449,"num_comments":0,"objectID":"44950084","points":3,"story_id":44950084,"title":"Building a self-hosted, fast AI research agent using OpenAI and SerpApi","updated_at":"2026-03-05T22:31:14Z","url":"https://serpapi.com/blog/building-a-fast-self-hosted-research-agent-with-openai-models-serpapi/"}],"hitsPerPage":50,"nbHits":1888,"nbPages":20,"page":0,"params":"query=hosted%C2%B7ai&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":12,"processingTimingsMS":{"_request":{"roundTrip":14},"afterFetch":{"format":{"highlighting":1,"total":1},"merge":{"total":1},"total":1},"fetch":{"query":3,"scanning":7,"total":11},"total":12},"query":"hosted\u00b7ai","serverTimeMS":14}