autoharness vs claude-reflect
Self-learning skill layer for Claude Code: distills skills from your real sessions, merges same-scenario ones, updates them in use and prunes the unused — touching only skills it wrote. — versus — Claude Code plugin that learns from your corrections — hooks capture them in-session, /reflect syncs approved learnings to CLAUDE.md/AGENTS.md, /reflect-skills mines history into reusable commands.
Both learn from your Claude Code sessions; claude-reflect syncs approved corrections into CLAUDE.md and commands, autoharness distills and maintains skills automatically.
| autoharness | claude-reflect | |
|---|---|---|
| Stars | 11k | 1.7k |
| Forks | 608 | 152 |
| Language | Python | Python |
| License | MIT | MIT |
| Last activity | 2 days ago | 8 days ago |
| Topics | skills, coding | coding, memory |
| Curated connections | 5 | 14 |
autoharness — the curator's take
Install it if you live in Claude Code and want lessons captured without curating skills by hand — zero config, zero deps, and it never touches skills you wrote or installed. Skip it off Claude Code, or if you need measured gains: skills survive on adherence, not a held-out score. Needs Python 3.11+ as `python3` on PATH, or its hooks stay off (macOS's stock /usr/bin/python3 is 3.9).
claude-reflect — the curator's take
Install claude-reflect the third time you catch yourself typing the same correction into Claude Code. It's the pragmatic take on agent memory: no vector DB, no service — hooks queue corrections, you review, markdown files get smarter, and the AGENTS.md sync means Codex/Cursor/Aider benefit too. The /reflect-skills pattern-mining is the sleeper feature: 15 similar requests become one command. When NOT: if you expect actual memory infrastructure (semantic recall, knowledge graphs) — this is disciplined note-taking with AI triage, personal-scale by design. Everything lands via human review, which is a feature, not friction.