integrations/ag2/v0.1.0
XTLS/Xray-coreintegrations/ag2/v0.1.0Sep 18, 2026by het0814
Upgrading?
AI Summary
First release of the AG2 integration, providing Memanto persistent memory tools (remember, recall, answer) for AutoGen agents.
Key Highlights
- Registration of Memanto tools for AG2 assistants
- Support for AG2 0.9.x schema
- OpenAI configuration helper for AG2
- Automatic installation of Memanto core
New Features
- `register_memanto_tools()` function
- `create_memanto_tools()` function
- `openai_llm_config()` helper
- `configure()` function
Full Release Notes
# Release Notes for memanto-ag2 v0.1.0 First release of **`memanto-ag2`** Memanto persistent memory as AG2 tools (`memanto_remember`, `memanto_recall`, `memanto_answer`). ## What's included - `register_memanto_tools(assistant, executor=..., agent_id=...)` — register tools on Assistant + UserProxy in one call - `create_memanto_tools(client, agent_id)` — same tools if you register manually - `openai_llm_config()` — helper for AG2 0.14+ OpenAI setup - `configure()` — optional defaults for API key, source, recall limit - Smoke script: `integrations/ag2/scripts/smoke_test.py` ## Install ```bash pip install memanto-ag2 pip install "ag2>=0.9,<1" # for live AG2 chat only ``` `memanto-ag2` installs **`memanto`** automatically. Use **`ag2`**, not **`a2g`**. ## Requirements - Python 3.10+ - `MOORCHEH_API_KEY` - AG2 **0.9.x** for chat examples (`ag2` 1.x not supported yet) ## Tests ```bash python -m pytest integrations/ag2/tests/test_tools.py -q ``` ## Full Changelog https://github.com/moorcheh-ai/memanto/commits/integrations/ag2/v0.1.0
Related Repositories
ollama/ollama★ 184,204
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
fatedier/frp★ 110,051
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
asheshgoplani/agent-deck★ 102,148
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
infiniflow/ragflow★ 92,611
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
gohugoio/hugo★ 90,198
The world’s fastest framework for building websites.