Tandem is the authority layer between AI agents and company tools: runtime policy for tools, memory, approvals, and audit trails.
AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.
R.A.I.N. Lab is an experimental scientific-agent architecture that separates fast local judgment, independent probabilistic evaluation, multi-agent deliberation, evidence, and authorization into distinct computational layers.🐙(Predates Karpathy's AutoResearch)
A presentation surface for coding agents: real file:line ranges, narration, and flow diagrams you can play — instead of five paragraphs of prose. Walk it, comment, submit. Code review, architecture walkthroughs, plans. Native, in Rust. Claude Code, Codex, Cursor, Amp.
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Human-in-the-loop annotation tool for AI workflows
Extracts claims from SOPs, policies and regulations, has a person approve or reject each one, then serves the approved set to agents over MCP - each claim carrying a byte range to its source sentence. Open Knowledge Format (OKF) bundles, no database.
Shepherd is an end-to-end AI Software Engineering platform that supervises the complete software delivery lifecycle—not just code generation, but planning, execution, testing, regression, governance, deployment, and continuous knowledge growth.｜Shepherd 将 AI 的一次性交付，转化为组织的长期软件工程资产。
Enterprise Control plane that runs AI agents in governed and disposable sandboxes
A multi-provider LLM framework for Rust.
A Slack-style hub for humans and AI agents — real-time channels, external agent bots, file-aware chat, and channel memory. Open-source & self-hostable & MacOS & IOS.
Your 24/7 software factory with all of your human and agent team mates in one digital office. An entire AI company at work: Copilot, Codex, Claude Code & OpenCode crews, multiplayer control, isolated worktrees, human approvals, and evidence-backed pull requests.
An embeddable agent runtime for Rust. Any task, any provider, in your process — with a permission boundary, a sandbox, and a durable trace you own.
A shared surface where a person and an agent work on the same page. The agent authors the UI, the person marks it, and the surface reads itself back in relations rather than coordinates.
A simple and beautiful human-in-the-loop GUI for answering questions from an AI coding agent such as Claude Code, either in the browser or on the go with your phone.
Red-pen your agent's homework — a TUI for line-commenting rendered markdown and sending the comments to your coding agent
Local-first AI agent platform with a Tauri desktop app and Rust CLI. Run governed tools, durable sessions, multi-agent workflows, modular packages, and one-shot effect permits.
Proxilion is the security layer for the agentic workforce. It turns managed AI agents into governed users by enforcing strict cryptographic boundaries on every API call to SaaS like Google Workspace, Salesforce, or Atlassian.
To associate your repository with the human-in-the-loop topic, visit your repo's landing page and select "manage topics."