Self-Evolving RAG for AI Agents — A cross-app persistent memory system where agents autonomously write, retrieve, and evolve their knowledge
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"adaptive-agent-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
<div align="center"> <img src="https://raw.githubusercontent.com/justforever17/adaptive-agent-mcp/main/assets/logo.svg" alt="Adaptive Agent MCP" width="500"> ### **Self-Evolving RAG for AI Agents** > *Agents don't just read memory — they write it.* [](LICENSE) [](https://www.python.org/downloads/) [](https://modelcontextprotocol.io) [](https://pypi.org/project/adaptive-agent-mcp/) [**中文**](README_zh.md) | **English** </div> --- ## Core Concept <table> <tr> <td width="50%"> ### Traditional RAG ``` User Input → Retrieve KB → Generate ↑ Read-only (Human-maintained) ``` </td> <td width="50%"> ### Self-Evolving RAG ``` User Input → Retrieve Memory → Generate ↑↓ Read + Write Agent autonomously evolves ``` </td> </tr> </table> **Key Differences:** | | Traditional RAG | Adaptive Agent MCP | |:---:|:---|:---| | Read | Retrieves pre-indexed documents | Dynamically accumulates at runtime | | Write | Human-maintained knowledge base | **Agent writes autonomously** | | Scope | Generic knowledge | **User-specific memory** | | State | Static data | **Continuously evolves** | --- ## How It Works ``` In Claude Code: "Remember, I prefer TypeScript" ↓ Agent automatically calls: • append_daily_log() → Record to daily log • update_preference() → Update preferences • extract_knowledge() → Extract knowledge graph ↓ In Antigravity: "What are my coding preferences?" ↓ AI: "You prefer TypeScript" ``` **Teach once, remember forever. Share across apps, never forget.** --- ## Getting Started ### Prerequisites 1. **Python 3.10+** 2. **Ripgrep (`rg`)**: **REQUIRED** for full-text search. (**Windows**: `choco ins…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.