Explore the directory

The A2A Java SDK is an official Java library for building and running agentic applications as Agent2Agent protocol servers and clients, with JSON-RPC, gRPC and REST transport support.

• Agent frameworks

A lightweight, CLI-first orchestration layer that runs a chosen set of AI coding agents and models on the same task in parallel, keeps each answer opaque and separate, and lets a developer compare them before acting.

• Coding agents
• Agent frameworks

A survey repository accompanying a paper on how large language model benchmarking has moved from static test sets, which risk data contamination from training corpora, to dynamic evaluation methods designed to avoid it.

• AI evals
• Papers

A Python domain-specific language for designing and running surveys and experiments with many AI agents and language models at once, for computational social science and market research.

• Agent frameworks

An adversarial code-review skill for AI coding agents in which one role finds possible bugs, a second challenges each claim, and a third decides what the evidence supports, defaulting to a scan-only, single-pass report.

• Agent skills
• Code quality

The official MCP server and Agent Skills from freee, letting an AI agent call freee's accounting, HR, invoicing, workforce, sales, IT-asset, outsourcing-management and e-signature APIs, with OAuth 2.0 and PKCE authentication.

• MCP servers

A multi-agent system framework for building large-scale, LLM-driven social simulations, supporting agents added or removed at runtime, live intervention during a run, and verification of agent behavior against model outputs.

• Agent frameworks

A native vLLM attention backend that quantizes the KV cache to fit three to five times more context in the same memory, without a calibration step and without changing the served model.

• Inference

A VS Code extension for discovering, installing and managing open-source MCP servers and AI agent skills, and exposing them to GitHub Copilot, Claude Code and Codex CLI from one panel.

• MCP servers
• Editors

A sample chat application and FastAPI backend that answers questions about rows in a PostgreSQL table using OpenAI chat models, hybrid vector and full-text search, and function calling to turn natural-language filters into SQL conditions.

• RAG
• Databases

A family of Arabic-first, generative speech-recognition models that treat transcription as audio-conditioned next-token prediction rather than CTC decoding, covering Modern Standard Arabic, major dialects, code-switched Arabic-English and English.

• Speech

A native desktop application for chatting with multiple AI providers, such as OpenAI, Claude, Gemini, Grok or a local Ollama model, searching local files and the web, running scripts, and delegating tasks to agent CLIs from one app.

• Coding agents
• Inference

A one-click, portable Windows installer for AI-Toolkit by Ostris, a training suite for image and video diffusion models, setting up an embedded Python, Git, Node.js, FFmpeg, PyTorch and a pinned Triton build with no system Python needed.

• Models
• Generative media

An open-source agentic RAG framework, built on Alibaba Cloud's PAI platform, that combines knowledge-base management, multimodal document understanding, a ReAct agent and MCP tool integration for enterprise question answering.

• RAG

A tmux-based terminal manager for running several AI coding agent CLIs, such as Claude Code, Codex, OpenCode, Grok Build and Gemini CLI, side by side, each in its own persistent session, with live status, prompt dispatch and diff review.

• Coding agents
• Terminals

A Java library that wraps the Ollama server's API, giving Java applications text generation, multi-turn chat, tool and MCP tool calling, embeddings and model management against local or remote Ollama models.

• Inference
• Libraries

An MCP server that connects AI assistants and IDEs to DuckDB's SQL engine, letting them query local DuckDB files, in-memory databases, S3-hosted databases and MotherDuck, browse catalogs, and switch connections at runtime.

• MCP servers
• Databases

A command-line tool that launches coding agents such as Claude Code, Codex or OpenCode against a model running locally or with a hosted provider, packaging models as standard OCI images so they move like containers.

• Coding agents
• Inference

An open-source coordination protocol, built on top of Git, that lets coding agents share their intent before they edit, so plans that would quietly conflict are flagged while every worktree is still clean.

• Coding agents
• Git

A local CLI and MCP server that gives coding agents a reusable codebase index: connections between files and functions, pattern findings with alternatives, and checks they can run as they work, without an account or API key.

• Agent memory
• Code quality

A file-first framework that turns a research goal into a recoverable, inspectable run, organizing focused skills into explicit workflows and preserving intermediate artifacts, evidence and decisions at every step.

• Agent frameworks
• Agent skills

A hands-on workshop repository that builds a two-agent AI system, a deep-research agent and a writing workflow, each served as an MCP server and connected to a coding-agent harness such as Claude Code or Cursor.

• Tutorials

A git-backed, zero-dependency library of debugging lessons that AI coding agents search asynchronously so they can reuse fixes already verified by another agent's session, rather than rediscovering the same bug.

• Agent memory
• Debugging

A free, open-source, self-hostable alternative to ChatGPT, built with Ruby on Rails, that lets a user bring their own API keys for OpenAI, Anthropic, Google or other providers and switch between them mid-conversation.

• Inference