openamnesia vincentkoc · PARTIAL
Agents are only as good as their context but most context lives in scattered traces: coding agent sessions, IDE chats, tool calls, and personal messages. We wanted a continual learning context engine that can securely extract memory from real activity, so agents can cold-start with high-signal history and stay current as you work
github.com/vincentkoc/openamnesia · ★ 30 · Forks 3 · Size 546 KB
SUMMARY
Technologies 21
Scored 17
Observed 17
Practices 6
Evidence 22
Skips 4
COVERAGE
Analyzed 167 files · 101 commits · 0 API calls
TECHNOLOGIES & DEPTH
TypeScript LANGUAGE Depth 70
25 files · PRODUCTION
Dockerfile LANGUAGE Depth 70
1 files · PRODUCTION
Shell LANGUAGE Depth 70
2 files · PRODUCTION
JSON LANGUAGE Depth 70
4 files · PRODUCTION
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
TOML LANGUAGE Depth 70
2 files · PRODUCTION
YAML LANGUAGE Depth 70
5 files · PRODUCTION
SQL LANGUAGE Depth 70
1 files · PRODUCTION
Python LANGUAGE Depth 70
113 files · PRODUCTION
npm BUILD_TOOL Depth 80
1 files · CONFIGURATION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
FastAPI FRAMEWORK Depth 62
2 files · PRODUCTION
Pydantic LIBRARY Depth 62
2 files · PRODUCTION
React FRAMEWORK Depth 74
8 files · PRODUCTION
React Router LIBRARY Depth 74
5 files · PRODUCTION
Ruff QUALITY Depth —
0 files · config only
Uvicorn LIBRARY Depth 58
1 files · PRODUCTION
Vite BUILD_TOOL Depth 44
1 files · PRODUCTION
mypy QUALITY Depth —
0 files · config only
pytest TESTING Depth —
0 files · config only
python-dotenv LIBRARY Depth —
0 files · config only
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · observedlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-02-06
Last commit 2026-04-30
Active months 3
Commits 101