Explore the directory

A self-hosted AI agent team that deploys real websites to your own Cloudflare account, subtitles and dubs video, and holds any destructive action for human approval, driven from a CLI, a web dashboard, or Telegram.

• Coding agents
• Hosting

An automated code-review tool that reviews every pull request with a model you choose, posts findings inline on the affected lines, and blocks a merge when it finds a serious issue.

• Code quality

A Model Context Protocol server that lets Claude query, create, update and manage Salesforce objects, records and Apex code using natural language.

• MCP servers

A library that lets a Frappe Framework application function as a Streamable HTTP Model Context Protocol server, registering existing app functions as MCP tools.

• MCP servers

An open-source assistant that turns a plain-language description of a business process into an editable BPMN diagram, refined through conversation and exported as a .bpmn file.

• Design tools

Identity infrastructure for autonomous agents that issues short-lived, cryptographically verifiable credentials, enforces delegated authority through chains of agents, and revokes access in real time.

• Auth

An enterprise gateway that sits between a team's chat channels and the AI agents acting on their behalf, keeping credentials out of the model's reach and logging every action to a signed, tamper-evident audit trail.

• Security

An agentic coding environment for running Claude in tmux with orchestration, memory and a live token monitor, paired with a standalone cross-model review gate that can block AI-written changes from merging.

• Coding agents
• Code quality

An unofficial PyTorch reproduction of DeepSeek's method for teaching multimodal LLMs to reason with bounding boxes and points interleaved directly in their chain of thought.

• Models

A platform for defining persistent AI agents in a plain-language format called Books, then deploying them to an Agents Server where they run continuously, remember context and work in teams.

• Agent frameworks

An open, provider-pluggable runtime that decides how much inference an AI request needs, spending extra model calls on verification only for higher-risk work and reporting the policy, cost and latency for every run.

• LLM gateways

An Elixir SDK implementing the Model Context Protocol, providing both client and server support built on Elixir's concurrency and fault-tolerance model.

• MCP servers

A YAML-configured runtime for building and operating multi-agent applications, run from a terminal Studio that shows evidence for every run, tracks a supervisor's goal to explicit completion, and gates memory promotion behind review.

• Agent frameworks

A Rust-native embedded graph-vector database that combines OpenCypher-style querying, vector search and graph algorithms in one system for GraphRAG, knowledge graphs and large-scale relationship analytics.

• RAG
• Databases

A hands-on multi-module course that builds a personal research assistant from a hand-rolled agent loop up through a deployed, secured production Model Context Protocol server.

• Tutorials

A local, whitebox vulnerability-research pipeline that builds a call graph across a codebase, enumerates every path from untrusted input to a dangerous operation, and uses a code-specialized LLM to judge which paths are exploitable.

• Security

A local knowledge-graph and hybrid-search server for Obsidian vaults that exposes an MCP server, an HTTP REST API and ChatGPT Actions so AI agents can search, read and edit notes.

• Agent memory
• RAG

A lightweight, self-contained Go tool that renders Markdown files locally in a browser with GitHub's own styling, without calling GitHub's API.

• CLI tools
• Documentation tools

A bilingual cybersecurity knowledge base for security researchers, service engineers, CTF players, and red-team learners, covering web and blockchain security, CTF, and incident response.

• Security

A general-purpose local tool-use agent with no cloud dependency, built to run on old or unusual hardware against any local LLM server, offering shell, git, file and web tools through a single dependency-free Python script.

• Coding agents

A multi-agent orchestration framework that splits omnimodal tasks into subtasks handled by specialized sub-agents equipped with perception and action tools, coordinated by a planning main agent.

• Agent frameworks

A self-hosted application server for deploying AI agents as production infrastructure, packaging orchestration, memory, tools, knowledge and access control into deployable units called formations.

• Agent frameworks

A macOS menu-bar tool that checks whether Codex is actually using the model you selected, by reading Codex's own per-turn model records and periodically fingerprinting the live model with a bias test on random-number generation.

• AI evals
• Desktop utilities

A terminal-native manager for local large language models that bundles a TUI, CLI, background daemon and OpenAI-compatible proxy around llama.cpp, with support for several other local inference backends.

• Inference
• Terminals