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.
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
| Date | Stars |
|---|---|
| 2026-08-04 | 344 |
| 2026-08-13 | 1095 |
| 2026-08-18 | 1438 |
| 2026-08-19 | 1440 |
| 2026-08-20 | 1441 |
| 2026-08-21 | 1447 |
| 2026-08-22 | 1449 |
| 2026-08-23 | 1451 |
| 2026-08-24 | 1452 |
| 2026-08-25 | 1451 |
| 2026-08-26 | 1450 |
| 2026-08-27 | 1445 |
| 2026-08-29 | 1447 |
| 2026-08-30 | 1448 |
| 2026-08-31 | 1449 |
| 2026-09-02 | 1450 |
| 2026-09-03 | 1452 |
| 2026-09-04 | 1453 |
| 2026-09-05 | 1451 |
| 2026-09-06 | 1449 |
| 2026-09-07 | 1451 |
| 2026-09-08 | 1453 |
| 2026-09-09 | 1454 |
| 2026-09-10 | 1451 |
| 2026-09-11 | 1451 |
| 2026-09-12 | 1452 |
| 2026-09-13 | 1454 |
| 2026-09-14 | 1454 |
| 2026-09-15 | 1454 |
| 2026-09-16 | 1455 |
| 2026-09-17 | 1454 |
| 2026-09-18 | 1454 |
| 2026-09-19 | 1452 |
| 2026-09-20 | 1454 |
| 2026-09-22 | 1456 |
| 2026-09-23 | 1455 |
| 2026-09-24 | 1454 |
| 2026-09-26 | 1453 |
| 2026-09-27 | 1453 |
| 2026-10-01 | 1452 |
| 2026-10-03 | 1451 |
| 2026-10-05 | 1452 |
| 2026-10-06 | 1453 |
| 2026-10-09 | 1454 |
| 2026-10-12 | 1457 |
| 2026-10-14 | 1459 |
| 2026-10-15 | 1458 |
| 2026-10-16 | 1459 |
| 2026-10-17 | 1460 |
| 2026-10-18 | 1461 |
| 2026-10-20 | 1459 |
| 2026-10-21 | 1460 |
| 2026-10-23 | 1462 |
| 2026-10-24 | 1443 |
| 2026-10-25 | 1441 |
| 2026-11-01 | 1442 |
| 2026-11-03 | 1442 |
| 2026-11-04 | 1442 |
Today
— stars today
This week
+1 stars this week
This month
-10 stars this month
Momentum
51.0
growth rate 0.07%/day
<h1 align="center">Paritok</h1>
<p align="center"><b>A non-destructive compression gateway for coding agents — cut your input-token bill without changing your agent.</b></p>
<p align="center">Paritok sits between your agent and the LLM as a drop-in proxy. On every request it strips the tool-schema bloat, compresses tool results and file reads, and summarizes stale history — then forwards upstream, billed on the compressed tokens. Nothing is ever permanently discarded: the agent pulls back any exact original on demand. Works with <b>Claude Code, Cursor, Codex, OpenHands</b>, and any agent that honors <code>BASE_URL</code> — <b>you don't change a line of your agent</b>.<br/><br/>Powered by the <b>first open-source 4B compression model trained specifically for coding agents</b> (45K real agent trajectories). Cut input token bills from <b>~25% on turn one</b> to <b>past 85% in long, context-saturated sessions</b>, and fit <b>~3× more turns</b> in the same context window.</p>
<p align="center">
<img src="./paritok-compression.png" alt="Paritok compression: 3,000 tokens shrunk to 780 with semantics intact" width="820"/>
</p>
<p align="center">
<a href="https://arxiv.org/abs/2608.24188">
<img src="https://img.shields.io/badge/arXiv-2608.24188-b31b1b?logo=arxiv&logoColor=white" alt="arXiv"/>
</a>
<a href="https://huggingface.co/paritok/paritok-4b-v1">
<img src="https://img.shields.io/badge/🤗%20Model-HuggingFace-yellow" alt="HF Model"/>
</a>
<a href="./LICENSE">
<img src="https://img.shields.io/badge/License-Apache_2.0-blue" alt="License"/>
</a>
<a href="https://discord.gg/SeBJE5Eucp">
<img src="https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&logoColor=white" alt="Discord"/>
</a>
<img src="https://img.shields.io/badge/backbone-Qwen3--4B-purple" alt="Qwen3-4B"/>
<img src="https://img.shields.io/badge/python-3.11+-blue" alt="Python"/>
</p>
<p align="center">
<a href="#-what-paritok-does">What it does</a> ·
<a href="#-the-three-levers">The three levers</a> ·
<a href="#-savings-compound-over-a-session">Compounding savings</a> ·
<a href="#-cost-impact">Cost</a> ·
<a href="#-pricing">Pricing</a> ·
<a href="#-quick-start">Quick Start</a> ·
<a href="#-the-engine-4b-compression-model">The engine (model)</a> ·
<a href="#-team">Team</a>
</p>
---
## 📢 News
- **2026-08-17** **v1.3.8** — a visual `/stats` dashboard (live token savings + per-request original→compressed before/after, in place of the raw JSON) and the new [Paritok VS Code extension](https://github.com/Paritok-official/paritok-vscode).
- **2026-07-31** **v1.3.0** — stability release: edit-recovery, `read_original` API rename (from `expand_context`).
- **2026-07-19** **v1.2.0** ships the embedding-based tool filter — the biggest single-turn lever (~29K → ~8K on a typical Claude Code turn), unlocking prompt-cache-friendly tool selection with `gateway_search_tools` recall.
- **2026-07-15** **Paritok gateway v1.0.0** open-sourced — the proxy/middleware that turns the 4B model into a drop-in Claude Code / Cursor / Codex compression layer.
- **2026-07-14** **Paritok-4B-v1** released on Hugging Face Hub with full SWE-bench Lite end-to-end evaluation.
- **2026-06-25** Finished training. 45K teacher-distilled samples on the Qwen3-4B backbone.
---
## 🚪 What Paritok does
Paritok runs as a **middle layer between your agent and the LLM API** — your agent points at Paritok instead of Anthropic/OpenAI, and everything else stays the same.
```
Your Agent (Claude Code / Cursor / Codex)
→ builds request (tool schemas + history + tool results / file reads)
★ Paritok gateway rewrites the request here ★
→ forwarded to Anthropic / OpenAI (billed on the compressed tokens)
← response flows back unchanged; compressed refs expand on demand
```
The token bill for a coding agent is dominated by **input you re-send every turn**: dozens of tool schemas, an ever-growing message histoExcerpt of 33,746 characters
Read on GitHub
63
22
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b8b6778b9f9ce2c0, topic:developer-tools