Explore the directory

A PyTorch library that trains a linear adapter with triplet loss to align retrieval query embeddings with real user queries, improving RAG search without retraining or re-indexing the embedding model.

• RAG
• Models

A local daemon that connects a user's local AI agents, such as an Ollama model, to the hybro.ai portal so local and cloud agents can be used side by side while local processing stays on the user's machine.

• Agent frameworks

An open-source Electron desktop client for the xAI Grok Build coding agent, giving the native grok CLI runtime a visual interface with parallel sessions, native tool execution and MCP support.

• Coding agents

An agent-driven framework that uses Claude Code sub-agents to iteratively optimize RTL timing, verifying every proposed transformation against the original design with sequential equivalence checking before promoting it.

• Coding agents
• Testing

A distributed, multi-agent autonomous system that bootstraps its own infrastructure from a single shell command on a blank Linux machine, then runs and evolves long-horizon agent tasks continuously.

• Agent frameworks
• Containers

A cross-agent workflow toolkit of seven steps for taking work from idea to merged PR, usable as Claude Code skills or Codex prompts, with shared on-disk state so either agent can pick up a task.

• Agent skills

A Tauri desktop launcher for the Codex CLI that bundles a task-board service, injects a taskboard panel into Codex's own interface, manages Codex configuration files, and installs an MCP runtime with one click.

• Coding agents

An offline, Windows-only local LLM coding assistant that bundles llama.cpp, Python and Git into one folder, indexing a project with a local RAG search and code graph to answer questions and propose file edits without cloud access.

• Coding agents
• Inference

A clipboard-monitoring tool that watches for code copied from any LLM chat, parses unified diffs, patches or full snippets, and applies them to the right files in an existing codebase automatically.

• Desktop utilities

A penetration-testing management platform for security researchers, tracking targets, findings and tool output, and building a knowledge graph of relationships between them to visualize attack paths.

• Security

An autonomous agentic system that turns a natural-language evaluation goal into a verified, executable benchmark dataset, covering requirement analysis, subtask design, data grounding and quality control.

• Agent frameworks
• AI evals

A Next.js app for testing MongoDB Atlas hybrid search, combining full-text and vector search queries through a unified $search stage with adjustable rank-fusion parameters.

• Databases
• Tutorials

A self-hosted, multi-agent platform where an orchestrator decomposes a goal into roles, dispatching implementation, code-review and verification agents that work together and stream their progress.

• Coding agents
• Agent frameworks

A collection of skills for AI coding agents, packaged in the Claude skills format and installable through a Claude Code plugin marketplace, the openskills tool, or as Nix modules for the rigup Agent Rig System.

• Agent skills

An MCP server and CLI that lets Claude Code agents delegate tasks to agents running in other project directories, each inheriting that project's own MCP servers, CLAUDE.md and tools.

• Coding agents
• MCP servers

A C++ implementation of quantized global parametrization for volumes, turning a tetrahedral mesh with a compatible input map into a valid integer-grid parametrization from which a defect-free hexahedral mesh can be extracted.

• Libraries

A gradient-free method for training neural networks, including spiking networks and other models without useful gradients, that perturbs parameters within a finite radius and updates them through a weighted optimal-transport barycenter.

• Models

A Python library and CLI that turns source documents such as PDFs into instruction fine-tuning datasets, grounding each generated example in a specific chunk of the source, grading it with an LLM judge, and deduplicating by embedding rather than exact text.

• Models

A modular Rust library for building durable AI agent memory systems, combining B-Tree, BM25 full-text and HNSW vector indexes in one embedded, schema-aware document database.

• Agent memory
• Databases

A demonstration project that uses Spring AI with Ollama or OpenAI to chat with documents stored in a library, embedding them into a PostgreSQL vector database to answer questions from their content.

• RAG
• Tutorials

UniAI is a Unity framework for adding AI chat, agents and tool use to a game or editor, with a unified provider layer for Claude- and OpenAI-compatible APIs, streaming responses, multimodal input, an MCP client and image generation.

• Agent frameworks

TreeHop is a lightweight, embedding-level query rewriter for multi-hop retrieval-augmented generation that updates and prunes query embeddings directly, instead of repeatedly calling an LLM to rewrite the query between retrieval hops.

• RAG

Sparrow is a spec-driven, domain-driven-design framework for AI coding assistants that turns raw business requirements into production code through an eight-step pipeline, using each tool's own native AI rather than a separate agent framework.

• Agent skills

SMART POLE is a systematic prompt-engineering framework that breaks a request into nine distinct categories of context - such as style, the user's expertise level, the goal, available resources and audience - intended to reduce vague or hallucinated answers from a language model.

• Agent skills