ilma
Framework-agnostic MCP server for agent memory with Postgres + pgvector, enabling persistent memory, recall, and task management across sessions.
README
ilma
Framework-agnostic agent memory system.
Postgres + pgvector backend. MCP-native. Hermes Agent, Claude, Cursor, Codex — any MCP client.
pip install ilma
ilma init
ilma status
What ilma is
ilma stores what your agents know — and makes it retrievable across sessions, frameworks, and machines.
- 8 memory surfaces: memories, wiki, journal, skills, metrics, kanban, observability, sessions
- Hybrid retrieval: vector + FTS + chunk-level reranking
- MCP server:
ilma-mcp— works with any MCP client - HTTP API: REST endpoints behind your own reverse proxy
- CLI:
ilma init,ilma search,ilma remember,ilma doctor - Postgres + pgvector: proven, backup-friendly, multi-client
Quick start
# Install
pip install ilma
# Initialize (9-step wizard: Postgres, extensions, schemas, embedder)
ilma init
# Store a memory
ilma remember "User prefers dark mode" --tags user,preference
# Search
ilma search "dark mode preference"
# Check health
ilma doctor
Architecture
MCP client (Claude, Cursor, Hermes, etc.)
↓ stdio / HTTP
ilma MCP server / HTTP API
↓ psycopg3
Postgres + pgvector
├─ ilma.memories
├─ ilma.wiki
├─ ilma.journal
├─ ilma.skills
├─ ilma.metrics
├─ ilma.kanban
├─ ilma.observability
└─ ilma.sessions
Project status
In active development. See PLAN.md for the execution roadmap.
Development
Install dev dependencies and set up pre-commit:
make install
pip install pre-commit
pre-commit install
Run all checks locally:
make all
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.