Repolode
Enviar
memodb-io

memodb-io/Acontext

Open-source memory layer that turns agent task outcomes into editable Markdown skill files shared across agents and LLMs.

Ver no GitHubSite
Estrelas
3,695
Forks
332
Issues abertas
37
Último commit
há 3 meses

O que é?

Acontext is a skill memory layer for AI agents. It captures learnings from agent sessions, such as what worked, what failed, and user preferences, and stores them as agent skill files instead of opaque embeddings. Developers can read, edit, version, and export these files as ZIP archives for use with other agents, LLMs, or frameworks.

Learning is triggered when a task is marked complete or failed. An LLM pass distills the conversation and execution trace, and a Skill Agent decides whether to update an existing skill or create a new one according to a SKILL.md schema the developer defines. Agents retrieve memory through tools like get_skill and get_skill_file, relying on tool use rather than semantic top-k search.

The project provides Python and TypeScript SDKs, a CLI for starting a self-hosted backend with Docker, and a web dashboard. It also includes a virtual persistent disk, sandboxed code execution with mountable skills, and context engineering features such as summaries and editing strategies.

Recursos principais

  • 01Stores learned knowledge as Markdown skill files that can be read and edited directly.
  • 02Lets developers define memory structure through a SKILL.md schema.
  • 03Retrieves memory via get_skill and get_skill_file tools instead of embedding search.
  • 04Exports skills as ZIP for use with other agents or LLMs.
  • 05Provides Python and TypeScript SDKs and a CLI for self-hosting with Docker.

Casos de uso

  • Giving a coding or support agent memory of user preferences that users can inspect and correct.
  • Letting an agent learn from failed tasks and reuse successful approaches in later runs.
  • Sharing one set of skill files across agents built on different frameworks.
  • Running a self-hosted memory backend for agent development and testing.

Tópicos

#agent-memory#llm#ai-agent#context-engineering#agent-skills#llmops#self-hosted#agent#agent-development-kit#agent-observability

Perguntas frequentes

O que é Acontext?
Open-source memory layer that turns agent task outcomes into editable Markdown skill files shared across agents and LLMs. Acontext is a skill memory layer for AI agents. It captures learnings from agent sessions, such as what worked, what failed, and user preferences, and stores them as agent skill files instead of opaque embeddings. Developers can read, edit, version, and export these files as ZIP archives for use with other agents, LLMs, or frameworks.
Acontext é gratuito? Qual é a licença?
Acontext é open source sob a licença Apache-2.0. Confira os termos da licença antes de usá-lo em produtos comerciais.
Acontext ainda é mantido?
Atualizado nos últimos 6 meses. O último commit de Acontext foi em 14 de jul. de 2026.
Para que posso usar Acontext?
Giving a coding or support agent memory of user preferences that users can inspect and correct. Letting an agent learn from failed tasks and reuse successful approaches in later runs. Sharing one set of skill files across agents built on different frameworks. Running a self-hosted memory backend for agent development and testing.
Onde consigo Acontext?
O código-fonte e as instruções de instalação estão no GitHub: https://github.com/memodb-io/Acontext

Resumo gerado por IA a partir do README do projeto. As estatísticas do GitHub são atualizadas diariamente.

Projetos relacionados