Explore the directory

A lean, A2A-native agent template built on LangGraph, meant to be forked: the boilerplate for the A2A protocol, tracing and the release pipeline stays fixed while a new agent's persona, prompts and tools become the fork's actual changes.

• Agent frameworks

A standalone C++ inference engine, built on the GGML tensor library, that runs ESMC protein language models on CPU with no Python, PyTorch or LibTorch at runtime.

• Inference

A desktop AI agent for Windows that executes terminal commands, manages files, writes and runs code, browses the web and reads the screen, acting on natural-language requests rather than only answering them.

• Workflow automation
• Browser automation

A self-hosted knowledge base where an AI agent not only answers questions over retrieval-augmented generation but also searches the web, fetches pages and writes newly found knowledge back into the index automatically.

• RAG

A self-hosted AI teammate that works entirely through GitHub: it picks up labeled issues, asks clarifying questions, opens pull requests, replies to review comments, resolves merge conflicts and can auto-merge when checks pass.

• Coding agents

A personal but reusable collection of extensions, tools, skills, a theme and settings for the Pi coding agent, packaged as separate installable npm packages that others can adopt individually.

• Agent skills

A conversational AI framework for .NET that orchestrates specialized agents through an actor-model architecture to classify and resolve customer inquiries with semantic routing and policy guardrails.

• Agent frameworks

A diagnostic and audit library for Mixture-of-Experts models in HuggingFace Transformers that instruments router modules to catch expert collapse, routing entropy collapse and load imbalance during training.

• Models
• Testing

The companion code repository for a Manning book on adapting open-weights language models, covering prompting and RAG, LoRA and QLoRA, full supervised fine-tuning, distillation and DPO/RLHF alignment on a single GPU.

• Models
• Books

A local web dashboard for reconnaissance and security testing of MCP endpoints, discovering exposed resources, tools and prompts and probing them for vulnerabilities such as injection, SSRF and path traversal.

• Security

A list of machine learning and data science tutorials with full implementation code, covering topics such as time-series forecasting, LoRA fine-tuning, GPU kernel design, document parsing pipelines and vector search.

• Tutorials

A self-updating index of LLM agent frameworks published on GitHub, refreshed every 15 minutes by a GitHub Actions cron job that discovers new repositories and ranks them by activity.

• Curated lists

A drop-in project template and set of governance conventions for running an autonomous coding agent such as Claude Code, Gemini CLI or Codex around the clock on a repository, with container isolation and a GitHub-driven review workflow.

• Coding agents

A macOS desktop app that runs Claude Code, Codex, Gemini CLI and Cursor side by side in separate git worktrees, with an MCP server so one agent can spawn and monitor others, plus on-device push-to-talk dictation.

• Coding agents

A Go-native framework for building, orchestrating and observing AI agents, with native OpenTelemetry tracing and an embedded dashboard shipped in the same binary.

• Agent frameworks

A self-hosted MCP server that turns an existing Obsidian or plain Markdown vault into searchable, durable memory for Claude Code, Codex, Cursor and other MCP-capable agents, with sourced, hybrid retrieval over a governed corpus.

• MCP servers
• Agent memory

A local-first desktop workspace where teams of AI agents build software, do research and automate browser tasks together, with per-agent models, permissions and a repository-aware coding mode.

• Coding agents
• Browser automation

A plugin for the DeepSeek Harness that implements the Agent2Agent protocol v1.0 as both a client and a server, letting one instance discover and call remote agents or expose itself to other agents.

• Agent frameworks

A serving system that lets multiple SGLang model instances share GPU memory by separating KV-cache capacity from FFN weight execution, so each model's resource needs no longer have to be reserved together.

• Inference

A tool that indexes a TypeScript codebase into a Neo4j code knowledge graph, so Claude Code and other AI coding agents can answer architecture questions in Cypher instead of relying on embedding similarity over code chunks.

• MCP servers
• Agent memory

An IntelliJ Platform plugin that embeds a multi-agent AI coding assistant directly into a JetBrains IDE, reading and editing project files, running terminal commands, searching the web and inspecting git history from one chat panel.

• Coding agents

An open-source application that turns long-form ESG corporate disclosures into searchable, cited evidence through retrieval-augmented generation and an optional knowledge graph.

• RAG

A modular PyTorch library for training and deploying Bangla language models from scratch, built around modern architecture components such as grouped-query attention, sliding-window attention, rotary embeddings and sparse mixture-of-experts.

• Models

A Chinese-language comparison guide to AI agent orchestration frameworks — Scion, AutoGen, CrewAI, LangGraph, MetaGPT, Swarms, Dify and Coze — with architecture analysis, code examples and a framework-selection decision tree.

• Agent frameworks
• Tutorials