Mnemo AI – Local agentic assistant for any LLM that learns from its failures
Mnemo AI is a local agentic AI assistant built with LangGraph and LangChain, supporting multiple LLM providers including Ollama, Bedrock, OpenAI, Anthropic, and more. It features MCP tool integration, RAG, user profile learning, episodic memory, and an ACE Playbook that learns from both successes and failures. The tool also offers web search, image analysis, file operations, bash execution, and many other capabilities.
Notifications You must be signed in to change notification settings
Fork 0
Star 3
BranchesTags
Open more actions menu
Folders and files
NameName
Last commit message
Last commit date
Latest commit
History
308 Commits
308 Commits
.github/workflows
.github/workflows
bash
bash
docs
docs
images
images
src/mnemoai
src/mnemoai
tests
tests
.gitignore
.gitignore
ARCHITECTURE.md
ARCHITECTURE.md
CHANGELOG.md
CHANGELOG.md
CLAUDE.md
CLAUDE.md
LICENSE
LICENSE
README.md
README.md
mkdocs.yml
mkdocs.yml
pyproject.toml
pyproject.toml
pytest.ini
pytest.ini
requirements-dev.txt
requirements-dev.txt
requirements.txt
requirements.txt
Repository files navigation
A local agentic AI assistant with MCP (Model Context Protocol) integration, RAG capabilities, and intelligent conversation management. Built on LangGraph with LangChain for multi-provider LLM support (Ollama, Amazon Bedrock, OpenAI, Anthropic, Amazon SageMaker AI, LiteLLM).
▶️ Watch the demo
📖 Documentation
Full documentation is available at https://brunopistone.github.io/mnemoai/
Getting Started
Usage
Configuration
Advanced Features
Productivity Tools
Architecture
Development
🚀 Quick Start
pip install mnemoai-assistant # or: uv tool install mnemoai-assistant mnemoai # verbose (shows thinking); --no-verbose to hide
On first run, if no config is found, an interactive configurator launches and walks you through picking a provider, model, and feature toggles — then writes ~/.mnemoai/config/config.yaml.
→ See the Getting Started guide for full setup.
✨ Key Features
🤖 Multi-Model Support: Ollama (local), Amazon Bedrock, OpenAI, Anthropic (Claude), Amazon SageMaker AI, LiteLLM (100+ providers)
🔧 MCP Tool System: Extensible tool architecture via Model Context Protocol
📚 RAG: Automatic document indexing and semantic (hybrid) search
🧠 User Profile Learning: Personalized responses learned from interactions
🧩 Episodic Memory: Learns from successful task completions and retrieves similar solutions
📖 ACE Playbook: Learns strategies from successes AND failures (Agentic Context Engineering)
🔍 Web Search & 🌐 Crawler: Brave Search API + web page extraction with RAG ingestion
🖼️ Vision Support: Image analysis with vision models
📁 File Operations & ✏️ Precise Editing: Read/write/edit text, CSV, JSON, PDF, DOCX
🔎 Fast Search: Glob + ripgrep content search (10-100x faster)
📋 Todo Tracking, 📝 Plan Mode & 🔄 Background Tasks: Multi-step task management
⚡ Bash Execution & 🛡️ Git Safety: Shell commands with smart error handling and guardrails
📄 License
Licensed under the MIT License — see the LICENSE file for details.
🤝 Contributing
This is a personal development project. Feel free to fork and adapt it to your needs; attribution to the original repository is appreciated but not required.
About
No description, website, or topics provided.
Resources
Readme
License
MIT license
Uh oh!
There was an error while loading. Please reload this page.
Activity
Stars
3 stars
Watchers
1 watching
Forks
0 forks
Report repository
Releases
75 tags
Packages 0
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Contributors
Uh oh!
There was an error while loading. Please reload this page.
Languages
Python 99.9%
Shell 0.1%