Stars
Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
Native micro Web UI for scripts and agents — super fast OS native webview with bidirectional JSON communication for agents
Our library for RL environments + evals
Agentic RL on Any Harness at Scale
ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.
Reference code for the Meta-Harness paper.
https://pypi.org/project/deepagents-sandbox/
The official implementation of the paper "MLP Memory: A Retriever-Pretrained Memory for Large Language Models". (ICLR 2026)
Python tool for converting files and office documents to Markdown.
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
💎 Robust job processing in Elixir, backed by modern PostgreSQL, SQLite3, and MySQL
Autonomous experiment loop extension for pi
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI…
Agent skill that generates rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps
A minimalist implementation of Agentic Memory architecture is DSPy
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
ParaView-MCP integrates multimodal LLMs with ParaView via Model Context Protocol, enabling natural language control of scientific visualizations. The agent observes the viewport for visual feedback…
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Open Source Semantic Search for your AI Agent
DeepLynx Nexus is version 2 of the DeepLynx data warehouse, and acts as the central integration point for the DeepLynx data ecosystem. Nexus is a functional data catalog and digital thread tool, al…