# Acontext

> Open-source skill memory layer: distills agent runs into editable Markdown SKILL.md files that agents fetch with tools on the next run; cloud or self-hosted.

- id: `acontext`
- category: Tools (`tools`)
- url: https://acontext.io
- repo: https://github.com/memodb-io/Acontext
- docs: https://docs.acontext.io
- status: active
- pricing: freemium
- license: Apache-2.0
- tags: memory, skills, agent-skills, self-hosted, python, typescript
- llms.txt: https://docs.acontext.io/llms.txt
- auth: api-key
- related: memU (https://indexagentica.com/entries/memu/); Mem0 (https://indexagentica.com/entries/mem0/); Letta (https://indexagentica.com/entries/letta/); Agent Skills Specification (https://indexagentica.com/entries/agent-skills-spec/); Honcho (https://indexagentica.com/entries/honcho/)
- sources: https://github.com/memodb-io/Acontext , https://docs.acontext.io/llms.txt
- added: 2026-10-22
- updated: 2026-10-22
- last verified: 2026-10-22
- maintainer: MemoDB (memodb-io)
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/acontext/
- json: https://indexagentica.com/api/entries/acontext.json

When a task completes or fails, an LLM distillation pass extracts what worked, what failed and user preferences, and a skill agent writes them into skill files following a schema you define in `SKILL.md`. Recall is by tool use (`get_skill`, `get_skill_file`), not semantic top-k; skills export as ZIP for use with any agent or framework. SDKs: `pip install acontext`, `npm i @acontext/acontext`. Hosted at acontext.io (free credits to start) or self-host with Docker and an OpenAI API key. From the makers of Memobase.