Explore the directory

A shared memory system that lets multiple AI agents, such as Claude Code running on different machines, store and recall facts, decisions and status through one Postgres-backed store.

• Agent memory
• Databases

An open-source command-line tool that unifies Ollama, vLLM and ComfyUI behind one endpoint on NVIDIA hardware, for running a private local inference stack without per-token cloud costs.

• Inference
• Hosting

A React Native library for on-device subject cutouts, image labeling and OCR, using Apple's Vision framework on iOS and Google's ML Kit on Android through Nitro Modules.

• Mobile
• Libraries

A control-plane platform for teams that puts humans and autonomous AI agents in the same projects, tasks and workflows, with shared context, role-based permissions and sandboxed execution.

• Agent frameworks

An iPhone and iPad app that runs Alibaba's Qwen3.5 models locally on the device using Apple's MLX framework, with optional tool use, image input and web search.

• Inference

A single local executable that runs and manages AI models across every GPU on a machine and turns them into a citation-backed search engine over a user's own files, notes, code and the web.

• RAG
• Inference

An evaluation framework and reference implementation for a multi-agent, graph-based retrieval-augmented generation method aimed at legal judgment prediction.

• RAG
• Papers

The official LangChain integration package for the Milvus vector database, providing vector storage, similarity search, hybrid search and retrieval-augmented generation support.

• RAG
• Databases

A dependency-free Python package for reading, writing and dequantizing GGUF model files, with a bundled graphical and command-line interface for chatting with a loaded model.

• Inference
• CLI tools

An orchestration daemon that watches GitHub issues and pull requests against configurable rules and automatically dispatches GitHub Copilot CLI sessions to work on them without a developer starting them by hand.

• Coding agents
• Git

A document-native framework that turned AI coding agents' tasks, decisions and verification evidence into repository files, so a new agent could resume from durable facts instead of chat history.

• Coding agents

A proof-of-concept tool that reads a React component library or a Figma design library into a shared, machine-readable contract, generates the other side from it, and compares both against that contract to catch drift between design and code.

• UI kits
• Design tools

A desktop GUI for managing Git worktrees, letting a developer work on several branches at once across multiple repositories with shared dependencies, a built-in terminal and MCP integration.

• Git
• Desktop utilities

A self-hosted MCP server that gives an AI coding agent persistent memory of past decisions, failed approaches and project context across sessions, machines and projects.

• MCP servers
• Agent memory

A set of Claude Code and Codex skills for prompt engineering, subagent dispatch decisions and building new skills, backed by an MCP server that measures whether a skill's description actually triggers.

• Agent skills

A self-hosted memory database for AI applications, combining Postgres and pgvector with hybrid search and a knowledge graph so decisions and context persist across sessions with an AI assistant.

• Agent memory
• Databases

A bridge that exposes a Language Server Protocol server's type information, cross-references and diagnostics to AI coding agents as Model Context Protocol tools, instead of plain-text code.

• MCP servers

A single Swift binary that gives AI agents and end-to-end tests zero-token, on-device computer vision on Apple Silicon, including OCR, pixel-exact UI targeting, and face grouping.

• Testing

A continuously running autonomous agent architecture that replaces cosine-similarity retrieval-augmented generation with a physics-simulated spatial memory, injecting far less context per turn.

• Agent frameworks
• Agent memory

A GGUF model inference engine written entirely in Rust, with quantized kernels for CPU, Apple Metal and CUDA, and an OpenAI-compatible server benchmarked directly against llama.cpp.

• Inference

A set of AI coding agents that read and enforce a team's own coding standards, written as machine-readable YAML rules layered from official, community and team-local sources.

• Agent skills
• Code quality

A runtime reliability layer for AI agents that runs deterministic, zero-model checks on every run to catch silent failures such as circular delegation, and can block an action before it executes.

• AI evals
• Debugging

A framework that lowers the cost of processing a dataset with large language models by deciding per record whether a cheap or an expensive model is used, guaranteeing a target accuracy.

• Inference
• Data engineering

A curated, open-source collection of more than one hundred prompts for the Seedream 4.5 image-generation model, with a searchable web gallery alongside the plain-text list.

• Generative media
• Curated lists