open-source

Runtime safety net for LLM agents that detects runaway token growth, classifies failure patterns, and suggests fixes without extra LLM calls. The project includes a Rust core, Python SDK, examples, benchmarks, and benchmark claims across multiple models and runs.

OpenRig is a local control plane for multi-agent coding topologies. It uses a YAML-based rig spec to boot, inspect, snapshot, restore, and visualize agent fleets, with examples like product teams, adversarial review, research clusters, and secrets management.

Open-source memory SDK for AI agents with persistent cross-session memory, graph relationships, semantic search, and AI-powered memory processing. Offers both self-hosted and cloud modes, plus MCP support for tools like Claude Code.

Deterministic, MCP-first browser automation runtime for coding agents. It exposes a public stdio MCP server with 50 browser tools, direct CDP control, and no API key or LLM fallback in the core path.

Open-source themed design systems for shadcn/ui, with 29 style variants and one-command installs through a shadcn registry.

Open-source AI coding agent focused on context curation and lower API cost. The repo describes hash-anchored edits, AST-based refactoring, parallel operations, and benchmark results against other agents.

DAC is a dashboard-as-code CLI and framework for building interactive dashboards from YAML and TSX, with a built-in semantic layer and an AI agent workflow for updating dashboards.

Open-source CLI that runs Codex, Claude, and Gemini in parallel on the same prompt, then synthesizes one answer and surfaces disagreements.

Agent Standup is an open-source tool that turns Claude Code sessions into a live stand-up-style view, showing which agents are working, waiting, blocked, or need input. It runs locally and supports VS Code, Cursor/Windsurf/VSCodium, terminals, a desktop app, and status line/tmux setups.

A safety proxy for AI agents that sits between agents and databases, checks SQL before execution, enforces per-agent policies, and supports approvals and rollback of a session’s changes.

A self-hosted personal AI assistant that runs in your own Cloudflare account. It includes chat, memory, tasks, notes, projects, and scheduled reminders, and can be deployed with a one-command installer.

A minimal embeddable coding agent in C with Rust/C extension support, static binaries, and a freestanding design aimed at low footprint and fast startup.

A Claude Code plugin that shows thumbnails for pasted images and opens an editor so you can annotate, crop, rotate, and label images before sending them to Claude.

Codync is an open-source tool for messaging coding agents like Claude Code, Codex, Cursor, Gemini, and others as persistent bots across iPhone, desktop, and terminal. It includes a Rust host, desktop apps, mobile support, approvals, notifications, and remote access features.

OpenTPU is an open-source AI accelerator project with RTL, ISA, simulator, compiler, profiler, and host software in one repo. The page shows it running real models like Qwen and LFM on a Kintex-7 PCIe card, with detailed performance results and documentation links.

A reputation layer for AI agents that tracks verified tasks, trust scores, and weekly leaderboards, with a CLI to register and run agents.

Deterministic gates for coding agents that block risky or pointless actions with code-based checks. The repo shows hook-based controls for delete protection, git safety, egress blocking, credential access, install pinning, loop detection, and idle-process handling across Claude Code, OpenAI Codex, and Antigravity.

Open-source Mac agent that operates inside one chosen window, asks before consequential actions, and verifies results after acting.

Open-source agent skill that finds and removes AI slop from writing while preserving the draft’s core meaning. It includes a local scoring workflow, browser/editor options, MCP access, and install paths for multiple assistants.

Open-source multi-agent harness for generating manufacturable CAD from plain-English briefs or sketches, using LLM agents, CadQuery Python code, renders, and DFMA checks.

Memex is an open-source tool for searching, browsing, and resuming transcripts from coding agents and IDE assistants like Claude Code, Codex, Cursor, and GitHub Copilot. It supports keyword and semantic search, token tracking, session reading, and multiple interfaces including CLI, TUI, web UI, and MCP.

A native macOS menu-bar app that shows Claude session and weekly usage limits with live reset countdowns, hover details, and configurable placement and refresh settings.

A local catalog for community agent skills with search, browsing, install commands, and static risk checks. It aggregates skills from multiple GitHub sources and includes a web dashboard for inspection and management.

Open-source agentic coding workspace for persistent agents, parallel sessions, and inspectable context across projects.