teilomillet / retrainLinks
a Python library that uses Reinforcement Learning (RL) to train LLMs.
☆42Updated 5 months ago
Alternatives and similar repositories for retrain
Users that are interested in retrain are comparing it to the libraries listed below
Sorting:
- ☆37Updated 5 months ago
- Leveraging DSPy for AI-driven task understanding and solution generation, the Self-Discover Framework automates problem-solving through r…☆72Updated 2 months ago
- ☆85Updated 4 months ago
- Letting Claude Code develop his own MCP tools :)☆122Updated 10 months ago
- CLI that uses DSPy to interact with MCP servers.☆23Updated 10 months ago
- Shared Memory Storage for Multi-Agent Systems☆138Updated 6 months ago
- ☆107Updated 2 months ago
- Qodo Commands Playbooks. Customize Qodo Command for your specific use case!☆114Updated 3 months ago
- ☆50Updated 4 months ago
- ☆55Updated 5 months ago
- DSPy module for OpenAI Codex SDK - signature-driven agentic workflows☆148Updated last month
- The theory of mind module for the SWE agent☆61Updated last month
- Thoughtful Lightning AI Assistant - Dual-engine system with DeepSeek reasoning and Groq inference, featuring Gradio UI, secure API manage…☆20Updated 11 months ago
- ollama like cli tool for MLX models on huggingface (pull, rm, list, show, serve etc.)☆122Updated last week
- OpenAI GPT hosted Agent Framework for Windows and MacOS☆36Updated last year
- Simple Graph Memory for AI applications☆90Updated 7 months ago
- 🧠 Advanced Claude streaming interface with interleaved thinking, dynamic tool discovery, and MCP integration. Watch Claude think through…☆185Updated 7 months ago
- Conduct in-depth research with AI-driven insights : DeepDive is a command-line tool that leverages web searches and AI models to generate…☆44Updated last year
- A framework for hosting and scaling AI agents.☆38Updated last year
- Deep research agents using MiniMax M2.1 interleaved thinking☆192Updated 3 weeks ago
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)☆90Updated last month
- ☆44Updated 6 months ago
- A collection of Compound Retrieval Systems implemented with DSPy and Weaviate.☆92Updated this week
- ☆19Updated 11 months ago
- Metadspy: The framework for specifying—not programming—language models☆87Updated 6 months ago
- Minimal agent runtime built with DSPy modules and a thin Python loop. Includes CLI, FastAPI server, and eval harness with OpenAI/Ollama s…☆66Updated 3 weeks ago
- Anthropic Computer Use with Modal Sandboxes☆42Updated last year
- A couple scripts to grab stats from email☆43Updated last year
- 🤖 Headless IDE for AI agents☆200Updated 3 months ago
- An OpenSource Deep Research library with reasoning☆170Updated last month