🌐 Website | 📚 Document What is Acontext? Acontext is an open-source skill memory layer for AI agents. It automatically captures learnings from agent runs and stores them as agent skill files — files you can read, edit, and share across agents, LLMs, and frameworks. If you want the agent you build to learn from its mistakes and reuse what worked — without opaque memory polluting your context — give Acontext a try. Skill is All You Need Agent memory is getting increasingly complicated🤢 — hard to understand, hard to debug, and hard for users to inspect or correct.
| Stars | 3,690 |
| Forks | 336 |
| Language | TypeScript |
| Category | AI 工具 |
| License | Apache-2.0 |
| Quality Score | 62.5322985643665/100 |
| Open Issues | 36 |
| Last Updated | 2026-07-14 |
| Created | 2025-07-16 |
| Platforms | node |
| Est. Tokens | ~2063k |
Explore other popular ai 工具 tools:
Acontext is Agent Skills as a Memory Layer. It is categorized as a AI 工具 with 3.7k GitHub stars.
Acontext is primarily written in TypeScript. It covers topics such as agent, agent-development-kit, agent-observability.
You can find installation instructions and usage details in the Acontext GitHub repository at github.com/memodb-io/Acontext. The project has 3.7k stars and 336 forks, indicating an active community.
Acontext is released under the Apache-2.0 license, making it free to use and modify according to the license terms.