Explore the directory

A Model Context Protocol server that exposes an existing GraphQL API's operations as MCP tools, giving an AI model a standard way to access and orchestrate it.

• MCP servers
• APIs

An MCP connector that gives an AI agent direct access to small judgment models such as Jev, CLM and Laya, returning a probability for each possible answer to a question instead of prose to parse.

• MCP servers

An agentic AI framework for designing, deploying and orchestrating multi-agent systems across distributed environments, with native agent-to-agent communication and a system that blocks dangerous agent actions before they execute.

• Agent frameworks

A solution accelerator, no longer maintained, that shows how to build a custom copilot for customer-facing teams using Azure OpenAI and Azure AI Search over an organization's own conversation data.

• RAG
• Tutorials

A config-driven tool for running experiments and evaluations of RAG search-and-response quality, testing different Azure AI Search and Azure OpenAI hyperparameters to find the best combination.

• RAG
• AI evals

An open-source harness for long, complex agent tasks that coordinates squads of expert agents, tracking task state so work can be checked, resumed after interruption, and carried forward across research, implementation and review.

• Agent frameworks

An enterprise AI agent platform for building, orchestrating and running security agents at scale, such as automated APK vulnerability analysis or penetration testing.

• Agent frameworks
• Security

A terminal-based, AI-agent-driven penetration testing tool that runs blackbox or whitebox tests against a target, and reports vulnerabilities with severity, evidence and suggested fixes.

• Security

A free, self-paced 24-week AI engineering course that takes a beginner from Python through machine learning, LLM internals, RAG, fine-tuning, agents and MCP, and cloud AI platforms, using one continuous case study.

• Tutorials

Open-source, self-hosted infrastructure for real-time voice AI telephony agents in Indian languages, with swappable speech-to-text, text-to-speech, LLM and telephony providers.

• Speech

An open-source, extensible agent framework for chatting with data, turning natural language into SQL, charts, dashboards and reports.

• RAG
• Data engineering

A hypergraph-driven retrieval-augmented generation method that models beyond-pairwise relationships between entities in domain-specific knowledge, to reduce hallucinations in medical LLM answers.

• RAG
• Papers

A standardized environment platform for agentic AI development and reinforcement learning, treating benchmarks, tools and even other agents as a single, swappable kind of environment.

• Agent frameworks
• AI evals

A Claude Code skill that has Claude author a dynamic workflow script and run it across a fleet of local Codex GPT agents, streaming the run back as a live, interactive execution map.

• Agent skills

A connector that gives an existing coding agent, such as Cursor, Claude Code, OpenCode or Codex, a presence in chat platforms like Slack, Telegram, Discord, Feishu, DingTalk, WeCom or WeChat, or embedded into another product.

• Coding agents
• Workflow automation

An open-source framework that gives an LLM agent control of a real Android phone or iPhone, letting it read the screen, tap, swipe and type through 62 MCP tools, with a choice of cloud, local or on-device models.

• Agent frameworks
• Mobile

A field guide to building and operating production AI-agent systems, covering agentic workflows, memory, context engineering, MCP and A2A interoperability, evaluation and multi-agent architecture.

• Books

A command-line tool that generates git commit messages with an LLM, analyzing the actual code change to explain why it was made, with support for more than 35 model providers.

• Git

A native desktop workspace for running multiple terminal coding agents, such as Claude Code, Codex, Cursor and Gemini, side by side, each in its own git worktree, with diffs reviewed in place.

• Coding agents

A command-line AI coding assistant built on DeepSeek Coder models, for code completion, refactoring, debugging and project scaffolding across many programming languages.

• Coding agents

A curated collection of prompt templates for ByteDance's Doubao AI, covering writing, coding, analysis and creative tasks, plus notes on prompting changes across Doubao model releases.

• Curated lists

A knowledge base and memory layer for AI coding agents that ingests session transcripts and connected data sources, and compiles them into a shared, agent-queryable wiki.

• Agent memory

Avaje-Inject is an annotation-processor-based dependency-injection library for server-side Java and Kotlin, generating wiring code at compile time instead of relying on runtime reflection or classpath scanning.

• Libraries

AReno is a self-contained toolkit for running reinforcement-learning post-training of language models, PPO, GRPO and SFT or DPO-style training, serving and agentic RL, on a single node without a training cluster.

• Models