RadarTopicsBuildersWeeklyReads
Open Source Radar
cheshire-cat-ai/

core

GitHubWebsite

Cheshire Cat AI (Stregatto) is a Python-based agent framework for education and research, focusing on making AI agents understandable and extensible via vibe coding. Latest releases include 2.0.23 as of 2026-07-08, with multiple past 2.x updates.

3.1kstars
411forks
6issues
GPL-3.0license
2023since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
headroomlabs-ai/
headroom
1.7k/wk

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

65k4.9kPython
sansan0/
TrendRadar
183/wk

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

61k25kPython
langgenius/
dify
753/wk

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

151k24kTypeScript
langchain-ai/
langchain
595/wk

The agent engineering platform.

143k24kPython
TauricResearch/
TradingAgents
693/wk

TradingAgents: Multi-Agents LLM Financial Trading Framework

96k18kPython
bytedance/
deer-flow
1.2k/wk

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

79k11kPython
Reviewgenerated from repository data · Aug 5, 2026

What it is

Cheshire Cat AI (Stregatto) is an AI agent framework intended for education and research, designed to be easy to understand and extend through vibe coding / agentic engineering. The project targets learning how AI agents work and publishing agents on the web.

How it works

The repository describes a framework for building AI agents with an emphasis on bottom-up clarity. It includes a quickstart sequence that involves initializing a bare project, adding Cheshire Cat AI, and running the agent, which exposes a UI at localhost:1865 and a REST API playground at localhost:1865/docs. The README notes that Version 2 is an unstable alpha with breaking changes and incomplete features.

Getting started

If starting from an empty folder:

uv init --bare
uv add cheshire-cat-ai
uv run ccat
- UI on http://localhost:1865
- REST API playground on http://localhost:1865/docs

License: GPL-3.0. Code is licensed under GPL3.

Recent releases

  • 2.0.23 2.0.23 (2026-07-08): Full Changelog: https://github.com/cheshire-cat-ai/core/compare/2.0.22...2.0.23
  • 2.0.22 2.0.22 (2026-07-04): fix: load bundled plugins on Windows by @davidegavio in https://github.com/cheshire-cat-ai/core/pull/1133
  • 2.0.21 2.0.21 (2026-06-22): Full Changelog: https://github.com/cheshire-cat-ai/core/compare/2.0.20...2.0.21
  • 2.0.20 2.0.20 (2026-06-22): Full Changelog: https://github.com/cheshire-cat-ai/core/compare/2.0.19...2.0.20
  • 2.0.19 2.0.19 (2026-06-21): What’s Changed: Update startup.py by @BDadmehr0; classify score_threshold as parameter, default 0.5, instead of magic …

Traction

Stars: 3081 Forks: 411 Open issues: 6

Behind the repo

Not provided in the README excerpt.

Caveats

Version 2 is described as unstable alpha with breaking changes and incomplete features. License: GPL-3.0. Created 2023-02-08. Last push 2026-07-29.

SharePost on XLinkedIn
All trending reposRevenue-verified startups →