Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.
| Date | Stars |
|---|---|
| 2026-07-31 | 315 |
| 2026-08-02 | 317 |
| 2026-08-12 | 320 |
| 2026-08-18 | 352 |
| 2026-08-19 | 354 |
| 2026-08-20 | 353 |
| 2026-08-21 | 353 |
| 2026-08-22 | 355 |
| 2026-08-23 | 355 |
| 2026-08-24 | 355 |
| 2026-08-25 | 359 |
| 2026-08-26 | 360 |
| 2026-08-27 | 361 |
| 2026-08-30 | 361 |
| 2026-08-31 | 360 |
| 2026-09-01 | 359 |
| 2026-09-02 | 360 |
| 2026-09-03 | 361 |
| 2026-09-04 | 363 |
| 2026-09-05 | 364 |
| 2026-09-06 | 365 |
| 2026-09-07 | 367 |
| 2026-09-08 | 367 |
| 2026-09-10 | 367 |
| 2026-09-11 | 369 |
| 2026-09-14 | 369 |
| 2026-09-15 | 370 |
| 2026-09-16 | 371 |
| 2026-09-18 | 372 |
| 2026-09-19 | 370 |
| 2026-09-20 | 370 |
Today
— stars today
This week
+1 stars this week
This month
+17 stars this month
Momentum
36.0
growth rate 0.27%/day
<div align="center">
<img src="media/logo.png" alt="OMNI Logo" width="300" />
<h1>OMNI</h1>
<p align="center">
<em><b>Your agent pays twice for output it has already seen.</b> OMNI hands back a retrievable handle instead: <b>97.2%</b> off a file it reads twice. Across a whole session it takes about a tenth of the repetition your work actually contains, which was <b>1.5%</b> of file-read bytes on the corpus below. How repetitive your work is decides where you land between those two. Nothing deleted, nothing invented, and every number here replays on your own history.</em>
</p>
[🇺🇸 English](README.md) | [🇯🇵 日本語](i18n/README-ja.md) | [🇨🇳 简体中文](i18n/README-zh.md) | [🇸🇦 العربية](i18n/README-ar.md) | [🇮🇩 Bahasa Indonesia](i18n/README-id.md) | [🇻🇳 Tiếng Việt](i18n/README-vi.md) | [🇰🇷 한국어](i18n/README-ko.md)
[](https://github.com/fajarhide/omni/actions/workflows/ci.yml)
[](https://github.com/fajarhide/omni/releases)
[](https://www.rust-lang.org/)
[](https://modelcontextprotocol.io/)
[](https://discord.gg/zHTuvZhF2M)
[](https://github.com/fajarhide/omni/blob/main/LICENSE)
[](https://hits.sh/github.com/fajarhide/omni/)
[](https://www.greptile.com/?utm_source=oss_badge&utm_medium=readme&utm_campaign=greptile_for_open_source)
</br></br>
```bash
brew install fajarhide/tap/omni && omni init
```
</br>
<img src="media/demo.gif" alt="OMNI distilling a noisy cargo test run down to the verdict, then omni stats" width="820" />
</div>
---
## What it does
**Drops the noise.** Build logs, Docker layer hashes, progress bars, ANSI colour. The
part of the output nobody reads is removed before it reaches the model.
**Stops re-sending what the agent has already seen.** A run of lines it was shown
earlier in the session comes back as one marker with a handle, not as the bytes again.
This is the half a filter cannot do: it removes bytes because they are already in the
context, not because a pattern calls them noise.
**Remembers across sessions.** Restart your editor or switch agents, and the project
context is still there.
**Gets out of the way.** A failing command passes through verbatim. JSON, YAML and CSV
are never touched. Most commands are handed back unchanged, and that is the intended
behaviour rather than a gap.
<img src="docs/website/src/media/where-omni-sits.svg" alt="OMNI runs as two hooks around a tool call: a pre-hook before the command, a post-hook that distills the output before the agent reads it, with everything it removes archived to a local SQLite database that omni retrieve reads back." width="820" />
It runs as two hooks around a tool call your agent host already makes. Nothing proxies
your shell, and the database never leaves the machine.
---
## The second read is free
An agent re-reads the same file constantly. Without OMNI it pays for every byte
again. With OMNI the second read is one marker carrying a handle, because those bytes
are already in its context, and `omni retrieve <hash>` hands the file back in full if
it is ever needed.
<table>
<tr>
<td align="center"><b>Without OMNI</b><br/><sub><code>cat</code> twice: the same 7.6 KB, twice</sub></td>
<td align="center"><b>With OMNI</b><br/><sub>second read 214 B, <b>97.2%</b> smaller</sub></td>
</tr>
<tr>
<td valign="top"><img src="media/demo-ledger-without.gif" alt="the same file read twice with no OMNI: two identical screens of source" width="400" /></td>
<td valExcerpt of 19,246 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f8b2f06f1fc07c06, llm:Repository description: 'Noise-canceling context and long-term memory for your AI agent. Stop paying Claude to read 10,000 lines of terminal noise like a headphone for AI agent' and topics including ai-agents, memory, memory-management, context-distillation, token-efficiency, token-optimization.
matched fp:f8b2f06f1fc07c06, llm:Repository description: 'Noise-canceling context and long-term memory for your AI agent. Stop paying Claude to read 10,000 lines of terminal noise like a headphone for AI agent' and topics including ai-agents, memory, memory-management, context-distillation, token-efficiency, token-optimization.
matched fp:f8b2f06f1fc07c06, llm:Repository description: 'Noise-canceling context and long-term memory for your AI agent. Stop paying Claude to read 10,000 lines of terminal noise like a headphone for AI agent' and topics including ai-agents, memory, memory-management, context-distillation, token-efficiency, token-optimization.