adaptive-agent-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@adaptive-agent-mcpRemember I prefer Python over JavaScript."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Self-Evolving RAG for AI Agents
Agents don't just read memory — they write it.
中文 | English
Core Concept
Traditional RAG
User Input → Retrieve KB → Generate
↑
Read-only
(Human-maintained)Self-Evolving RAG
User Input → Retrieve Memory → Generate
↑↓
Read + Write
Agent autonomously evolvesKey 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 |
Related MCP server: knowledge-base-server
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
Python 3.10+
Ripgrep (
rg): REQUIRED for full-text search. (Windows:choco install ripgrep, macOS:brew install ripgrep)SQLite: Handled automatically by Python.
Configuration (v0.6.0)
Configuration is managed via Environment Variables.
1. mcp.json Structure
{
"mcpServers": {
"adaptive-agent-mcp": {
"command": "uvx",
"args": ["adaptive-agent-mcp"],
"env": {
"ADAPTIVE_EMBEDDING_BASE_URL": "https://api.xxx.cn/v1",
"ADAPTIVE_EMBEDDING_API_KEY": "sk-your-xxx-key",
"ADAPTIVE_EMBEDDING_MODEL": "Qwen/Qwen2.5-Coder-7B-Instruct",
"ADAPTIVE_RERANK_BASE_URL": "https://api.xxx.cn/v1",
"ADAPTIVE_RERANK_API_KEY": "sk-your-xxx-key",
"ADAPTIVE_RERANK_MODEL": "BAAI/bge-reranker-v2-m3"
}
}
}
}Local Models:
Ollama: Set
ADAPTIVE_EMBEDDING_PROVIDERtoollama.LM Studio/vLLM: Set
ADAPTIVE_EMBEDDING_PROVIDERtoopenai_compatible.Base URL: Set to your local endpoint (e.g.,
http://localhost:11434/v1orhttp://localhost:1234/v1).API Key: Any string.
2. Environment Variables
All variables are prefixed with ADAPTIVE_.
Variable | Description | Default |
| Storage location |
|
| Path to | Auto-detect |
| Embedding provider ( |
|
| API Endpoint |
|
| API Key |
|
| Embedding Model |
|
| Rerank provider ( |
|
| API Endpoint |
|
| API Key |
|
| Reranker Model |
|
Default storage path:
~/.adaptive-agent/memory. All apps share the same memory.
Enhance Agent Memory Behavior (Optional)
If your AI doesn't actively read/write memory, add this to your system prompt or user rules:
## Memory System Instructions
- At the start of each conversation, call `initialize_session` to load user preferences.
- When user says "remember", "save", or expresses preferences, call `update_preference` or `append_daily_log`.
- After completing tasks, briefly record progress using `append_daily_log`.
- When user asks about past conversations, use `query_memory_headers` or `search_memory_content`.Features
Feature | Description | Version |
Three-Layer Memory | MEMORY.md + Daily Logs + Knowledge Items | v0.1.0 |
Scope Isolation |
| v0.2.0 |
Concurrent Safety | Cross-process file locking + async locks | v0.3.0 |
Incremental Indexing | mtime-based smart updates | v0.3.0 |
Hybrid Search | Vector + FTS5 with RRF fusion | v0.6.0 |
Rerank Service | Cohere-compatible re-ranking for higher precision | v0.6.1 |
Area Partitioning | Scope-based knowledge routing | v0.6.0 |
Knowledge Graph | NetworkX-based entity relations | v0.5.0 |
Async Foundation | Non-blocking I/O throughout | v0.6.0 |
Available Tools (14 tools)
Session & Retrieval
Tool | Description |
| Initialize session with user profile and recent context |
| Index scan — browse memory file metadata |
| Read complete memory file content |
| Full-text search using ripgrep |
Memory & Knowledge
Tool | Description |
| Intelligently update user preferences |
| Append content to daily log or knowledge items |
| Hybrid search (Vector + FTS5 + RRF fusion) with browse fallback |
| Soft-delete knowledge items |
| Aggregate weekly/monthly logs for summaries |
| Save period summaries |
Knowledge Graph
Tool | Description |
| Extract entity relations from text |
| Manually add relations |
| Query entities, relations, or stats |
| Multi-hop reasoning queries |
Storage Structure
~/.adaptive-agent/memory/
├── MEMORY.md # User preferences (scope-based)
├── knowledge/
│ └── areas/
│ ├── general/items.json # Global knowledge
│ ├── chat/items.json # Chat-scope knowledge
│ ├── coding/items.json # Coding-scope knowledge
│ ├── writing/items.json # Writing-scope knowledge
│ └── projects/{name}/items.json # Project-specific knowledge
├── .index/
│ ├── vectors.db # SQLite + sqlite-vec + FTS5
│ └── index.json # Indexer metadata
├── .graph/
│ └── knowledge.json # NetworkX graph
├── .locks/ # File lock directory
└── memory/
└── 2026/
└── 02_february/
└── week_07/
└── 2026-02-10.md # Daily logsData Safety
Isolated storage: Data stored in
~/.adaptive-agent/memory, independent of uvx installationConcurrent safety: filelock prevents data corruption from multiple clients
Human-readable: All data in Markdown/JSON format, easy to backup and version control
License
MIT License - See LICENSE for details.
Adaptive Agent MCP — Where agents learn, remember, and evolve.
This server cannot be deployed
Maintenance
Related MCP Connectors
Universal memory runtime for AI agents — episodic, semantic, and procedural memory.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
- memoryOAuthcom.humaux
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
Private, portable memory and reusable skills for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA knowledge-graph-based memory system for AI agents that enables persistent information storage between conversations.6-
- AlicenseNot gradedqualityCmaintenanceA persistent memory system that captures, classifies, synthesizes, and retrieves knowledge for AI agents, turning raw information into refined, retrievable knowledge that compounds intelligence over time.6 npm178MIT
- AlicenseNot gradedqualityDmaintenanceA-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.35MIT
- FlicenseNot gradedqualityCmaintenanceAn agentic memory system that enables AI assistants to store, search, and manage persistent memories with semantic understanding using natural language instructions.-