[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:acontext":3},"\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdiscord.acontext.io\" rel=\"nofollow ugc noopener\">\n      \u003Cimg alt=\"Acontext - Agent Skills as a Memory Layer\" src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fmemodb-io\u002Facontext\u002FHEAD\u002Fassets\u002FAcontext-header-banner.png\" \u002F>\n  \u003C\u002Fa>\n \t\u003Cp align=\"center\">\n \t  \t\u003Ca href=\"https:\u002F\u002Facontext.io\" rel=\"nofollow ugc noopener\">🌐 Website\u003C\u002Fa>\n      |\n \t  \t\u003Ca href=\"https:\u002F\u002Fdocs.acontext.io\" rel=\"nofollow ugc noopener\">📚 Document\u003C\u002Fa>\n  \u003C\u002Fp>\n  \u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Facontext\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Facontext.svg\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@acontext\u002Facontext\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F@acontext\u002Facontext.svg?logo=npm&logoColor=fff&style=flat&labelColor=2C2C2C&color=28CF8D\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmemodb-io\u002Facontext\u002Factions\u002Fworkflows\u002Fcore-test.yaml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fmemodb-io\u002Facontext\u002Factions\u002Fworkflows\u002Fcore-test.yaml\u002Fbadge.svg\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmemodb-io\u002Facontext\u002Factions\u002Fworkflows\u002Fapi-test.yaml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fmemodb-io\u002Facontext\u002Factions\u002Fworkflows\u002Fapi-test.yaml\u002Fbadge.svg\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmemodb-io\u002Facontext\u002Factions\u002Fworkflows\u002Fcli-test.yaml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fmemodb-io\u002Facontext\u002Factions\u002Fworkflows\u002Fcli-test.yaml\u002Fbadge.svg\" \u002F>\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003Cp align=\"center\">\n \t  \t\u003Ca href=\"https:\u002F\u002Fx.com\u002Facontext_io\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002Facontext_io?style=social\" alt=\"Twitter Follow\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fdiscord.acontext.io\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdynamic\u002Fjson?label=Acontext&style=flat&query=approximate_member_count&url=https%3A%2F%2Fdiscord.com%2Fapi%2Fv10%2Finvites%2FSG9xJcqVBu%3Fwith_counts%3Dtrue&logo=discord&logoColor=white&suffix=+members&color=36393f&labelColor=5765F2\" alt=\"Acontext Discord\" \u002F>\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003C\u002Fdiv>\u003Ch2>What is Acontext?\u003C\u002Fh2>\n\u003Cp>Acontext is an open-source skill memory layer for AI agents. It \u003Cstrong>automatically\u003C\u002Fstrong> captures learnings from agent runs and stores them as \u003Cstrong>agent skill files\u003C\u002Fstrong> — files you can read, edit, and share across agents, LLMs, and frameworks.\u003C\u002Fp>\n\u003Cp>If you want the agent you build to \u003Cstrong>learn from its mistakes\u003C\u002Fstrong> and \u003Cstrong>reuse what worked\u003C\u002Fstrong> — without opaque memory polluting your context — give Acontext a try.\u003C\u002Fp>\n\u003Ch2>Skill is All You Need\u003C\u002Fh2>\n\u003Cp>Agent memory is getting increasingly complicated🤢 — hard to understand, hard to debug, and hard for users to inspect or correct. Acontext takes a different approach: if agent skills can represent every piece of knowledge an agent needs as simple files, so can the memory.\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Acontext builds memory in the agent skills format\u003C\u002Fstrong>, so everyone can see and understand what the memory actually contains.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Skill is Memory, Memory is Skill\u003C\u002Fstrong>. Whether a skill comes from one you downloaded from Clawhub or one you created yourself, Acontext can follow it and evolve it over time.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>The Philosophy of Acontext\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cstrong>Plain file, any framework\u003C\u002Fstrong> — Skill memories are Markdown files. Use them with LangGraph, Claude, AI SDK, or anything that reads files. No embeddings, no API lock-in. Git, grep, and mount to the sandbox.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>You design the structure\u003C\u002Fstrong> — Attach more skills to define the schema, naming, and file layout of the memory. For example: one file per contact, one per project by uploading a working context skill.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Progressive disclosure, not search\u003C\u002Fstrong> — The agent can use  \u003Ccode>get_skill\u003C\u002Fcode> and \u003Ccode>get_skill_file\u003C\u002Fcode> to fetch what it needs. Retrieval is by tool use and reasoning, not semantic top-k.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Download as ZIP, reuse anywhere\u003C\u002Fstrong> — Export skill files as ZIP. Run locally, in another agent, or with another LLM. No vendor lock-in; no re-embedding or migration step.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>How It Works\u003C\u002Fh2>\n\u003Ch3>Store — How skills get memorized?\u003C\u002Fh3>\n\u003Cpre>\u003Ccode class=\"language-mermaid\">flowchart LR\n  A[Session messages] --> C[Task complete\u002Ffailed]\n  C --> D[Distillation]\n  D --> E[Skill Agent]\n  E --> F[Update Skills]\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cul>\n\u003Cli>\u003Cstrong>Session messages\u003C\u002Fstrong> — Conversation (and optionally tool calls, artifacts) is the raw input. Tasks are extracted from the message stream automatically (or inferred from explicit outcome reporting).\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Task complete or failed\u003C\u002Fstrong> — When a task is marked done or fail\u003C\u002Fli>\n\u003C\u002Ful>\n",1785715923085]