tigerless-labs/autoharness
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
About the project
A Claude Code plugin that distills skills from your real sessions, merges similar ones, updates those in use, and prunes unused ones. Runs as a Python hook and MCP server with no third-party dependencies.
Useful for
- Install the plugin and let it accumulate skills from your working sessions automatically
- Run /learn after solving a task to keep the lesson immediately
- Tune reflection cadence via AUTOHARNESS_REFLECT_EVERY_N to match your workflow
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 21 stars so far today, about 26 expected by the end of the day.
- Interest is fading: the two-day pace is 14% of the previous week and a half.
- About 5 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 4,359
- Stars in a day
- 26
- Forks
- 305
- Issues and pull requests
- 166
- Watchers
- 148
- Language
- Python
- License
- MIT
- Created
- June 9, 2026
- Last push
- September 4, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 16, 2026Top new repositories in the last 4 months: #95
- September 15, 2026Top new repositories in the last 4 months: #94
Similar projects
-
8.8
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.
-
8.5
tamaratran/fast-jev-compaction
Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…
-
7.9
hypit-ai/hypit
Hypit gives AI agents a language and system to create video: the agent clones a viral clip as an editable workflow — footage, captions, B-roll and effects anchored to words instead of seconds.
-
7.9
Tencent/BrowserSkill
BrowserSkill connects AI agents (Cursor, Claude Code, Codex, etc.) to your already logged-in browser via the bsk CLI and an extension, letting the agent work in a separate window without interrupting you.
-
7.0
korcarc/text-humanizer
A Python tool that rewrites AI-generated text through an LLM and translation pipeline to bypass detectors like Turnitin and GPTZero. Supports 8 languages and requires a DeepSeek API key.
-
6.8
Tencent/WeKnora
Open-source LLM knowledge platform: turns raw documents into queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.