Sign in
← Back to search
github Not archived

coleam00/claude-memory-compiler

Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything into structured, cross-referenced knowledge articles - inspired by Karpathy's LLM Knowledge Base architecture.

1 awesome list

Quick read

Stars
1,301
Forks
327
Open issues
24
Commits
2

Activity and growth

Latest capture 2026-10-16 03:14

Stars · last 7 days
0 0.0%
Commits · last 7 days
0 0.0%
Stars since tracking
+220
Stored snapshots
8

Classification

Technology stack

Starlette

Metadata

Language
Python
Default branch
main
Created
2026-04-06
First commit
2026-04-06
Last pushed
2026-04-06
GitHub updated
2026-10-15
Last synced
2026-10-16 03:14
Stack scanned
2026-10-16 03:14
Archived
No

Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.

Sign in to like coleam00/claude-memory-compiler
README View on GitHub

AI development signals

3 paths

Agent instructions and tool configuration found in this repository.

Agent instructions

Claude Code 2

View paths

Growth history

Tracked growth

8 observed captures since 2026-05-23. Observed captures are shown by default.

Stars from first capture +220

Chart data

Observed captures only

Time horizon

All tracked data

Custom date range

Stars history

Observed snapshots

Commits history

Observed snapshots

Similar repositories

Nearest indexed repositories by embedding similarity.

SamurAIGPT/llm-wiki-agent

A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.

3,551 stars
Python 2 awesome lists

20alexl/claude-engram

The flight recorder for Claude Code. Persistent memory across sessions, hook-level capture of every edit, error and decision, and a bracket around /goal so an unattended run cannot poll all night, lose its record, or die silently. Nothing self-reported: the run report is what the hooks saw.

16 stars
Python 1 awesome list

sbusso/claudeclaw

Use Claude to orchestrate agents like OpenClaw

194 stars
TypeScript 1 awesome list

Abilityai/cornelius

AI-powered second brain template for Claude Code + Obsidian

108 stars
Python 1 awesome list