Explore the directory

A decentralized semantic routing protocol that resolves natural-language intents to specialized agent endpoints in under 10 milliseconds using a local vector index, avoiding the latency and cost of routing tool calls through a cloud LLM.

• Agent frameworks

A Microsoft accelerator that deploys a multi-modal RAG pipeline on Azure Kubernetes Service using ColPali, a vision-language model that embeds document pages as images to preserve layout, tables, and charts without OCR.

• RAG
• Containers

A modular Python multi-agent framework, paired with a ready-to-run browser workbench called ModexBot, for building agent teams that share models, tools, memory, and workflows.

• Agent frameworks

A multiplayer AI agent harness for infrastructure work that runs one shared agent across Slack, Telegram, and a terminal at once, with shared project memory, scheduling, and human-approval gates for risky commands.

• Agent frameworks

An MCP server that gives AI assistants such as Claude and VS Code Copilot the ability to run pylint and pytest, plus other Python quality tools, against a Python project and get LLM-friendly results.

• MCP servers
• Code quality

A lightweight, asyncio-based Python library for building and simulating multi-agent systems, aimed at researchers and engineers who need reproducible agent behavior and controlled experimental conditions.

• Agent frameworks

A Python GUI for generating llama.cpp server launch commands, with a machine-learning-driven optimizer that searches thread, batch, and KV-cache settings for the best measured performance on the user's hardware.

• Inference

A companion HR policy question-answering example that reimplements the same guarded RAG workflow as an explicit LangGraph state graph, with visible per-node execution traces instead of a linear chain.

• RAG
• Tutorials

An HR policy question-answering example built with LangChain LCEL that classifies whether a question is in scope before retrieving from a local FAISS index, refusing to answer out-of-scope questions.

• RAG
• Tutorials

A managed, low-code platform with a visual flow builder for creating and deploying agentic GenAI applications, combining a vector database, integrations, and model access behind a deployed GraphQL API.

• Agent frameworks
• Workflow automation

Research code for a knowledge-graph-based RAG method that retrieves relevant subgraphs from large external knowledge graphs to augment LLM prompts for the schema-matching and data-integration task.

• RAG
• Papers

A pure-Go, no-cgo local LLM inference engine distributed as a single static binary, running open-weight models such as Gemma, Qwen, and Llama from safetensors or GGUF with schema-constrained structured output.

• Inference

A team-level control plane for coding agents, providing a Kanban board, a durable DAG workflow engine, and container-isolated execution so a team can see what an agent is running, its cost, and its output.

• Coding agents
• Workflow automation

A deterministic planning layer that turns discrete llama.cpp GGUF quantization presets into a near-continuous model-size control, spending a fixed byte budget on the most useful tensor-level precision upgrades.

• Inference

A RAG application that turns any documentation URL into a searchable, chat-based knowledge base, scraping and indexing the site and answering questions with source-backed citations.

• RAG

An AI agent framework built around a deterministic governance engine that validates, authorizes, and audits every agent action, using control theory and statistical estimation to keep agents from drifting from policy.

• Agent frameworks
• AI evals

An open-source, self-hosted knowledge backend that gives AI agents persistent, searchable memory over uploaded documents or existing storage, through an MCP server, REST API, or CLI, built on .NET.

• Agent memory
• RAG

Shared, reviewable memory infrastructure for coding agents: an organization publishes Markdown guidance that projects subscribe to, agents retrieve it while working, and any agent-proposed changes need human review before publishing.

• Agent memory

A reverse proxy for coding agents such as Claude Code, Codex CLI, and Cursor that filters each request's MCP tool catalog down to only the tools relevant to the current task, cutting token overhead.

• MCP servers
• LLM gateways

A high-performance, Rust-built vector search database aimed at high-load AI and RAG systems, reporting an order-of-magnitude higher throughput than Qdrant in the project's own benchmarks.

• Databases

A research framework, published at ICLR'26, that decomposes multi-hop questions into a query subgraph and traverses a graph of document chunks to retrieve reasoning-aligned context for RAG at a fraction of the LLM cost of prior methods.

• RAG
• Papers

A curated, machine-verified list of over 13,000 live web apps built with AI, automatically re-checked for liveness every few days and regenerated from the One's Vibe app directory.

• Curated lists

A self-hosted platform for running an agentic software development lifecycle against local LLMs, using rootless Podman or Docker containers with HashiCorp Vault and mandatory GPG-signed commits.

• Coding agents
• Inference

A tool that adds persistent memory, tree-sitter code intelligence, and multi-agent orchestration to AI coding assistants such as Claude Code, OpenCode, and Codex CLI.

• Agent skills
• Agent memory