Skip to main content
Glama
Feynman520

self-improve

by Feynman520
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

self-improve

한국어: README.ko.md

An agent-neutral self-improvement loop for coding agents (Claude Code, Codex). The more you work with the agent, the more it adapts to you: the moments you correct it are captured, and when the same lesson recurs the fix is applied automatically — a rule in your instruction file, a skill, or a guarded script — with a one-line notice and a one-phrase undo.

Everything stays on your machine. There is no telemetry.

What it does

① capture   — the agent logs a correction moment (or a nightly miner finds one in session transcripts)
      ↓
② detect    — the server notices the same lesson has recurred (2nd time; 3rd for taste/misread lessons)
      ↓
③ apply     — a rule line is written into a managed block of the narrowest AGENTS.md/CLAUDE.md that covers the affected projects
      ↓
④ grow      — procedural lessons become skills (synced to every agent), repeated manual work becomes a guarded script
      ↓
⑤ learn     — every use reports success/correction; scripts earn trust, bad artifacts retire, "R-003 빼" reverts anything

Piece

How

Records

one markdown file per lesson, SELF_IMPROVE_DIR/records/ (default .self-improve/ in cwd)

Ripeness

token-overlap similarity tuned on real Korean/English lessons; the model confirms before applying

Rules

written only inside <!-- self-improve:begin … end --> in AGENTS.md (or CLAUDE.md); human text untouched; per-file cap; file lock

Level

narrowest common ancestor folder that already has an instruction file, never above root

Skills

authored centrally in SELF_IMPROVE_DIR/skills/<name>/SKILL.md, copied to each agent's skills dir as si-<name>

Scripts

SELF_IMPROVE_DIR/scripts/, must use _guard.mjs / _guard.py: preview by default, --apply to run, auto-trusted after 3 successes

Registry

registry.json maps every artifact ↔ records ↔ version ↔ trust; fixes go to the existing artifact instead of a duplicate

Mining

cli.js nightly scans Claude (projects/*.jsonl) and Codex (sessions/**/rollout-*.jsonl) transcripts for user corrections, tool errors and repeated tool loops → candidate queue

Never automated

secrets, permissions, deploys, deletes, billing — the instructions forbid putting these in auto artifacts

Related MCP server: MCP Standards

MCP tools

Tool

Purpose

log

save a record; returns ripe (recurrence reached) and recurrence_of_resolved (a fixed lesson came back)

pending

call at session start: ripe clusters, escalations, mined candidates (≤3), retire suggestions

apply_rule

write a rule into the managed block, register it, resolve the records

register_artifact

register a skill (synced to agents) or a guarded script

feedback

success / correction for an artifact → trust, promotion, retirement

revoke

undo an artifact; its records become rejected so it is never re-applied

dismiss

drop a mined candidate

search / stats / resolve

query records, recurrence rate, artifact counts; manual resolve (rule existence is verified)

Install

git clone https://github.com/Feynman520/d06-p01-self-improve
cd d06-p01-self-improve
set SELF_IMPROVE_DIR=C:\path\to\central\store      # optional but recommended (one store for all projects)
node server/cli.js install --root C:\path\to\workspace --codex --schedule

  • --root writes the agent instructions into the root AGENTS.md managed block (creates AGENTS.md + CLAUDE.md shell if missing) so every agent reads the same instructions.

  • --codex registers the MCP server in $CODEX_HOME/config.toml.

  • --schedule registers the nightly transcript miner (Windows Task Scheduler; prints a crontab line elsewhere).

  • Claude Code: /plugin marketplace add Feynman520/d06-p01-self-improve → /plugin install self-improve@self-improve, and add SELF_IMPROVE_DIR to the plugin env.

Requires Node.js ≥ 18. Zero runtime dependencies.

CLI

node server/cli.js install [--root DIR] [--codex] [--schedule]
node server/cli.js mine [--days N]      # scan transcripts now
node server/cli.js nightly              # mine + link sessions + log to <store>/logs
node server/cli.js backfill [--apply]   # first-run: cluster existing open records → proposal (dry-run by default)
node server/cli.js status

Config (SELF_IMPROVE_DIR/config.json)

{
  "root": "C:\\workspace",
  "path_aliases": { "C:\\old\\workspace": "C:\\workspace" },
  "rule_cap": 30,
  "ripe_threshold": { "default": 2, "오해": 3 },
  "mine_days": 30,
  "candidates_per_session": 3,
  "retire_after_days": 60
}

Undo

Say to the agent: 규칙 R-003 빼 / remove rule R-003 / 그 스킬 빼. The line, skill or script is removed, the artifact retired, and its records marked rejected.

License

MIT

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • TOOT (Train of Operadic

    sancovp
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables context capture and reinforcement learning by recording successful work patterns and creating reasoning chains for cross-conversation continuity. Automatically captures positive feedback through Claude Code hooks to build reusable success patterns.
    -

  • MCP Standards

    airmcp-com
    A
    license
    B
    quality
    F
    maintenance
    A self-learning AI standards system that automatically detects patterns from user corrections and updates AI configuration files. Learns from repeated corrections (like 'use uv not pip') and automatically generates CLAUDE.md and other AI assistant configuration files.
    9
    3
    MIT

  • Claude Error Collector

    henningziech
    F
    license
    B
    quality
    D
    maintenance
    An MCP server that enables Claude to learn from user corrections by recording them as persistent rules in CLAUDE.md files. It manages project-specific or global guidelines to ensure the assistant avoids repeating the same mistakes in future sessions.
    2
    4
    -

  • Self-Learning MCP

    ByronAP
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to learn from their work by recording tasks, extracting patterns, detecting mistakes, and proactively surfacing insights, all using the agent's own model through a cooperative intelligence pattern.
    MIT