Explore the directory

A Java framework and runtime for building multi-agent AI systems on the JVM with explicit governance: human approval gates, spending budgets, tool access policies and durable execution that survives restarts.

• Agent frameworks

A git-native tool that records which AI coding agent wrote which line of a commit, signs each attribution record with ed25519, and stores it in the repository's own git history.

• Coding agents
• Git

A long-running, append-only benchmark that checks whether a frontier language model quietly gets worse after it ships, running the same frozen prompts and graders daily against a fixed baseline set by launch day.

• AI evals

A Python framework for declarative document indexing, where typed schemas describe what to extract from a document and Ennoia runs the extraction, stores the structured output, and serves combined filter and vector search over it.

• RAG

The repository for a W3C Community Group that develops draft reports on autonomous agents operating on the web, covering interoperability and how sites can express what an agent is and is not allowed to do.

• Agent frameworks

A local-first context-compression pipeline for Claude Code that uses hybrid BM25 and embedding retrieval plus AST-aware code chunking to reduce how many tokens of a codebase are sent to the model.

• Agent memory
• RAG

An embedded, ACID-compliant database that combines SQL tables, vector and keyword search, and a bi-temporal knowledge graph in one engine and file, and assembles token-budgeted context for an LLM in a single query.

• RAG
• Databases

A local coding agent that runs entirely on the developer's machine, working in any codebase through a terminal chat interface or the Agent Client Protocol for editors such as Zed and Xcode, with no API key or cloud round trip required.

• Coding agents

The official research code for an ECCV 2026 paper on quantizing every part of a multi-agent cooperative perception system for autonomous vehicles, aimed at cutting inference and communication cost with minimal loss of perception accuracy.

• Models
• Papers

A SQL-like query language and command-line shell for the Qdrant vector database, letting a developer write insert, search and filter statements instead of calling the Qdrant Python client directly.

• RAG
• Databases

A benchmark dataset of 1,475 document pages that evaluates document-parsing and OCR models on text, formulas, tables and reading order, matched across clean, digitally degraded and real-world scanned versions of the same pages.

• AI evals

An open, executable benchmark that scores how well large language models write 1C:Enterprise (BSL) code, judging generated code on syntax, meaning, optimization and platform fit by actually compiling and running it.

• AI evals

An ultra-lightweight personal AI agent written in Delphi Object Pascal, offering a command-line assistant, tool calling, MCP integration, an HTTP gateway with a web UI, scheduled tasks and skills.

• Agent frameworks

An MCP server that exposes the Paperclip AI agent orchestration platform's REST API as about 95 tools, aimed at the person operating a company of agents rather than the agents doing the work.

• MCP servers

A local retrieval and maintenance layer for a Markdown knowledge base such as Obsidian or Logseq, indexing notes into SQLite with full-text search, embeddings and a link graph, and exposing it to any MCP client.

• MCP servers
• RAG

A hands-free macOS voice loop for Claude Code that transcribes speech on-device, types it into the terminal window running Claude, and speaks the replies back in a chosen voice.

• Coding agents
• Speech

An Android app implementing the Mobile-Agent autonomous agent framework, letting a vision-language model such as GPT-4o or Claude see a phone's screen and operate it by tapping, swiping and typing to complete a task described in natural language.

• Agent frameworks
• Mobile

A TypeScript library built on the MCP SDK that adds authentication and authorization to Model Context Protocol clients and servers.

• MCP servers
• Auth

A self-hosted runtime for long-running AI agents that keep memory across sessions, load skills on demand, call MCP tools, run scheduled automations, and optionally coordinate sub-agents.

• Agent frameworks
• Agent memory

A Rust inference engine that runs a 28.9-million-parameter language model on an ESP32-S3 microcontroller, ported from a C reference implementation and benchmarked to run faster than it.

• Inference

A set of 116 Claude Code skills, rules and commands that let an agent assemble and edit 1C:Enterprise metadata objects, forms and extensions from compact JSON and validate them against the rest of a configuration.

• Agent skills

A marketplace plugin that installs agents, skills, hooks and slash commands for Claude Code and GitHub Copilot CLI, adding a session protocol and review gates for governed AI-assisted development.

• Coding agents
• Agent skills

A reproducible vLLM Docker image built specifically for the NVIDIA DGX Spark's GB10 chip, with every component in the stack pinned by commit or digest so the same version file always rebuilds the same image.

• Inference
• Containers

The companion source repository for the Packt book "LLVM Code Generation", offering a chapter-by-chapter, tag-marked implementation of an LLVM backend built from scratch on top of the LLVM 20.1.1 release.

• Tutorials