memodb-io/Acontext

Agent Skills as a Memory Layer

67
/ 100
Established

This helps AI agent developers enable their agents to learn from interactions and reuse successful approaches. It takes conversation logs and execution traces as input, distills key learnings, and stores them as human-readable Markdown 'skill files'. Developers of AI agents, especially those using large language models, will use this to give their agents persistent, understandable memory.

3,154 stars. Actively maintained with 116 commits in the last 30 days.

Use this if you are building AI agents and want them to autonomously learn, remember what works, and avoid repeating mistakes by storing knowledge in transparent, shareable skill files.

Not ideal if you need complex, hidden memory structures or are not working with AI agents that can benefit from discrete, file-based skill storage.

AI agent development LLM application building agent memory management machine learning engineering conversational AI
No Package No Dependents
Maintenance 22 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 20 / 25

How are scores calculated?

Stars

3,154

Forks

296

Language

TypeScript

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

116

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/memodb-io/Acontext"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.