Fastmcp Chroma Ollama
Local memory system for LLM assistants using ChromaDB, Ollama, and FastMCP
Ask AI about Fastmcp Chroma Ollama
Powered by Claude Β· Grounded in docs
I know everything about Fastmcp Chroma Ollama. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
FastMCP ChromaDB Memory Server
Overview
A sophisticated, local memory system for AI assistants using ChromaDB, Ollama, and FastMCP. This project provides a persistent, semantically-aware memory storage and retrieval system with advanced features like memory importance scoring, automatic merging, and intelligent pruning.
π Features
- π§ Semantic Memory Storage
- π Local-first Architecture
- π High-Performance Vector Search
- π€ Ollama Embedding Support
- π Memory Importance Scoring
- π Advanced Retrieval Mechanisms
π Requirements
- Python 3.10+
- UV Package Manager
- Ollama
- ChromaDB
- FastMCP
π¦ Installation
1. Install UV Package Manager
# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
2. Install Ollama
curl https://ollama.ai/install.sh | sh
ollama pull nomic-embed-text
3. Install Project
# Clone the repository
git clone https://github.com/bjkemp/fastmcp-chroma-ollama.git
cd fastmcp-chroma-ollama
# Create virtual environment
uv venv
# Activate virtual environment
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install project
uv pip install -e .
π Usage
Starting the Server
# With stdio transport (for Claude Desktop)
uv run -m fastmcp_memory.server --transport stdio
# With SSE transport
uv run -m fastmcp_memory.server --transport sse --port 8080
Basic Python Example
from fastmcp_memory import MemoryManager
async def example():
manager = MemoryManager()
# Store a memory
memory_id = await manager.add_memory("The capital of France is Paris")
# Retrieve memories
memories = await manager.retrieve_memories("France's capital")
print(memories)
π§ͺ Development
Setup Development Environment
# Install development dependencies
uv pip install .[dev]
# Run tests
uv run pytest
# Run code formatters
uv run black src tests
uv run isort src tests
π Project Structure
fastmcp-chroma-ollama/
βββ src/
β βββ fastmcp_memory/
β βββ __init__.py
β βββ server.py
β βββ server_core.py
β βββ ...
βββ tests/
βββ .github/
β βββ workflows/
βββ pyproject.toml
βββ README.md
βββ TODO.md
βββ LICENSE
π€ Contributing
Contributions are welcome! Please check our TODO.md for current development priorities and see our contribution guidelines.
π License
MIT License - See LICENSE for details.
πΊ Roadmap
Check out TODO.md for detailed development plans and future directions.
