ai
Orchestrate AI agents to find real vulnerabilities in code.
An open-source, self-hosted security research platform that turns focused AI analysis into de-duplicated, ranked findings with configurable validation and enrichment.
Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.
OpenConnector is an open-source connector gateway for AI agents and an alternative to Composio. Connect user app accounts once, then expose a shared catalog of 1,000+ providers and 10,000+ prebuilt Actions to agents and applications.
Give the agent a cage, not your keys.
Give the agent a cage, not your keys. One-command Docker sandbox for AI coding agents: full autonomous permissions, per-project isolation, your host stays untouched.
The open agent runtime.
Open, self-hostable agentic runtime for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.
A Visualization Language for the AI Era.
Flint is a visualization intermediate language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs. Instead of requiring verbose low-level parameters such as scales, axes, spacing, and layout, the Flint compiler derives optimized chart settings from the data, semantic types, chart type, and encodings. Flint supports 46 chart types, and it supports rendering in Vega-Lite, ECharts, and Chart.js.
The video editor built for AI.
Let AI tools like Claude and Codex directly read and edit your multi-track timeline. Generate images and videos inline using the latest models.
Local code intelligence for MCP.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Run LLMs at home, BitTorrent-style.
You load a part of the model, then join a network of people serving its other parts. Single‑batch inference runs at up to 6 tokens/sec for Llama 2 (70B) and up to 4 tokens/sec for Falcon (180B) — enough for chatbots and interactive apps.
Agentic SAST Pipeline.
VVAH is Visa's open-source harness for autonomous vulnerability discovery, remediation, and validation using frontier AI models, built on learnings from Project Glasswing (Anthropic's initiative for AI-assisted vulnerability research).
Open AI Artifact Metadata.
Hugging Bay publishes open AI catalog metadata, source provenance, license records, neutral hosted-file inventory, answer packs, and recorded hashes. Canonical bundle verification and runtime readiness remain unknown.
Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.
Mesh LLM pools GPUs and memory across machines and exposes the result as one OpenAI-compatible API at http://localhost:9337/v1. Start one node, add more nodes later, and let the mesh decide whether a model runs locally, routes to a peer, or uses Skippy stage splits for models that are too large for one box.
top-style TUI for monitoring AI coding agent sessions.
Your window into what your AI coding agents are doing, sitting in the terminal, where you run them. agtop is a top-style terminal dashboard that tracks every Claude Code and Codex session on your machine: spend, token usage, context pressure, CPU load, tool invocations, and more. All in one place, live.
A Self-Hosted AI Workspace.
A self-hosted AI workspace for chat, agents, research, documents, email, notes, calendar, and local model workflows.
Related contents:
Run AI locally on your Mac.
Local AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.
Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.
AI Builder Real World Apps. Open-source app builder engine — intent to working app.
The open-source Convergence App Builder. Generate a working app from intent, then verify every agent turn against its business requirements.
AI SRE AgenticOps for Kubernetes and cloud infrastructure. Your infrastructure can explain itself, heal safely, and prove it recovered.
Flawless is an AI-native SRE control plane for Kubernetes and cloud infrastructure. It connects alerts, evidence, topology, human approval, controlled remediation, and recovery verification in one auditable AgenticOps loop.
cost control for AI agent loops. Your AI agent loops don't know when to stop. LoopGain does.
When an agent keeps checking and revising its own work, it often spins on a problem it can't solve — or talks itself into an answer worse than one it already had. LoopGain watches the loop as it runs, stops it at the right iteration, and keeps the best version, not the last.
ReactBench is an evaluation for coding agents on realistic React work. Models can pass every test in today’s benchmarks and still write React that fails in production. Tests verify behavior, but they miss React performance, accessibility, and quality issues.
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Related contents:
Run the Moebius inpainting model in the browser.
Paint over a region of an image to replace it; the denoising loop runs locally on your GPU. The first run downloads ~1.27 GB of weights from Hugging Face (then browser-cached). A WebGPU-capable browser (recent Chrome or Safari) is required.
Related contents:
Engineer loops to improve project quality, aligning your team and agents on what quality means for what matters most.
Hand the agent the keys. Without actually handing it the keys. HASP is a local-first broker for managed secrets in agent workflows.
A local broker that holds your secrets in one encrypted vault and hands them to apps and coding agents when needed, only inside the project boundary, only for the window you allow, and never as a value the agent can see.
Agents need credentials to run tests, call APIs, and deploy code. Copying those credentials into prompts, shell history, .env files, or repo-local notes makes the agent faster today and harder to trust tomorrow. HASP keeps secrets in a local encrypted vault and gives commands only the values they are allowed to use at runtime.
Intercept any app, then call it from Python like a library.
A visualization tool that replays coding-agent sessions on a 3D map of your codebase.
Empowering your AI Agents. Instant, Concurrent, Secure & Lightweight Sandbox Service for AI Agents.
Cube Sandbox is a high-performance, out-of-the-box secure sandbox service built on RustVMM and KVM. It supports both single-node deployment and easy scaling to multi-node clusters. It is compatible with the E2B SDK and can create a hardware-isolated, fully serviceable sandbox in under 60ms with less than 5MB of memory overhead.
Otari Gateway is the open-source gateway that puts a single OpenAI-compatible API in front of many LLM providers.
Run it in your own infrastructure. Use it standalone, or connect it to otari.ai for hosted routing, authentication, and usage reporting.
Simple CLI tool for deterministic routing of queries between local and hosted LLM models.
A fast, offline hard-or-easy call on every prompt — scored deterministically, with no model call. Route the easy ones to your small/local model and the hard ones to your big one, or compose any model-router behind it.
The Agent Client Protocol (ACP) standardizes communication between code editors/IDEs and coding agents and is suitable for both local and remote scenarios.
Related contents:
autonomous red teaming platform; multi-agent offensive-security meta-harness.
A multi-agent offensive-security framework, built to turn the AI coding agent you already run into a zero-day hunter.
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
Control HermesFrom your iPhone
A native iPhone client for your self-hosted Hermes agent. Open sessions, stream responses, steer model / profile / reasoning, attach files, and browse your workspace — all from your phone. The agent runs on your server, not your iPhone.
Reusable GitHub Action that reviews Terraform PRs for security, cost, and style using a LangGraph multi-agent system, posting a single severity-ranked comment.
This project is an AI-Native SAST tool. Unlike traditional SAST tools that rely solely on parsing and analysis rules, this project uses LLM (e.g. Claude from Anthropic, GPT from OpenAI or Gemini from Google) to find vulnerabilities.
An open source registry and proxy that federates MCP, A2A, and REST/gRPC APIs with centralized governance, discovery, and observability. Optimizes Agent & Tool calling, and supports plugins.
ContextForge is an open source registry and proxy that federates tools, agents, and APIs into one clean endpoint for your AI clients. It provides centralized governance, discovery, and observability across your AI infrastructure.
The Open-Source AI Visibility & GEO Tracker.
Free and open source. Track how your brand appears inside ChatGPT, Gemini, Perplexity, Claude, and Google AI Overview while using your own accounts, on your own infrastructure.
A format specification for describing a visual identity to coding agents. DESIGN.md gives agents a persistent, structured understanding of a design system.
🦋 An Infographic Generation and Rendering Framework, bring words to life with AI!
AntV Infographic is AntV's next-generation declarative infographic visualization engine. With a carefully designed infographic syntax, it can quickly and flexibly render high-quality infographics, making information presentation more efficient and data storytelling simpler.
OpenWiki is a CLI that writes and maintains documentation for your codebase, built specifically for agents.
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
Related contents:
Subscribe once. Read by email or over MCP.
Antenna stores your feed subscriptions in one local SQLite index, then routes new posts to email and to AI agents over MCP from the same data. No vendor cloud. No proprietary lock-in. Your subscription graph lives in a file you control.
Related contents:
Architecture Enforcement Framework for AI-Assisted Development.
Guardian turns software architecture into executable constraints. Instead of relying on documentation, code reviews, and tribal knowledge to prevent architectural drift, Guardian continuously verifies that implementations conform to architectural decisions throughout development.
Semantic DataFrames for humans and agents.
fenic turns AI-assisted exploration of structured and unstructured data into reusable, inspectable DataFrame pipelines.
It's a DataFrame query engine for semantic data processing, with AI operators — extract, classify, summarize, embed, semantic join, and more — built into the query model. Use it to turn documents, transcripts, logs, eval traces, tickets, tables, and APIs into typed rows and repeatable workflows.
Free AI Gateway for Multi-Provider LLMs.
Never stop coding. Free AI gateway: one endpoint, 231+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini. RTK+Caveman stacked compression saves 15-95% tokens, smart auto-fallback, MCP/A2A, multimodal APIs, Desktop/PWA.
OKF is a universal, vendor-neutral format for representing knowledge as plain markdown files with YAML frontmatter. It is not tied to any particular agent, framework, model provider, or serving system.
Related contents:
AI-Native Open-Source Design Tool.
The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to Pencil.
Open reimplementation of Sakana Fugu — the 'one model to command them all' LLM orchestrator. Read → run → train → serve.
An open, runnable reverse-engineering of Sakana AI's Fugu — the "one model to command them all" LLM orchestrator.
Fugu is sold as a single model; it is really a policy over models — a tiny coordinator that, per query, routes work to a pool of frontier LLMs and returns one answer. Sakana's product and trained weights are closed. OpenFugu rebuilds the mechanism from the two papers + released artifacts, verifies it against real weights, trains a Conductor of our own, and serves it behind one OpenAI-compatible endpoint. Four stages, all working: read → run → train → serve.
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
Related contents:
Design principles for agent ergonomics. Higher accuracy with lower token cost than both MCP and regular CLI.
AXI is a new paradigm - agent-native CLI tools built from 10 design principles that treat token budget as a first-class constraint.
Related contents:
HTML is the new markdown. Lavish is the new editor for your HTML artifacts.
Lavish Editor opens agent-generated HTML files in a local browser, lets you pinpoint elements or selected text and send feedback to the agent to address.
Related contents:
Before I go to bed, I tell my agents: good night, have fun.
gnhf is a ralph, autoresearch-style orchestrator that keeps your agents running while you sleep — each iteration makes one small, committed, documented change towards an objective. You wake up to a branch full of clean work and a log of everything that happened.
Related contents:
Manage worktrees without managing worktrees.
Treehouse helps you manage a pool of reusable, isolated worktrees so each of your agents gets its own environment instantly — no cloning, no conflicts, no coordination overhead.
Related contents:
The OWASP Gen AI Security Project is an OWASP Flagship Project and global, open-source initiative dedicated to identifying, mitigating, and documenting security and safety risks associated with generative AI technologies, including large language models (LLMs), agentic AI systems, and AI-driven applications. Our mission is to empower organizations, security professionals, AI practitioners, and policymakers with comprehensive, actionable guidance and tools to ensure the secure development, deployment, and governance of generative AI systems.
Related contents:
The open source control plane for AI inference.
Modelplane is software you install and run in your own environment to orchestrate models, the serving stack, and the infrastructure underneath across cloud, neocloud, and on-premise. It runs any model on any engine on any infrastructure, from a single GPU to disaggregated, multi-node deployments. Built on Crossplane, it is an active system that continuously reconciles your fleet toward the state you declare: provisioning inference clusters, scheduling deployments onto compatible clusters, scaling replicas, caching weights, and routing traffic.
Related contents:
git push no-mistakes
no-mistakes puts a local git proxy in front of your real remote. Push to no-mistakes instead of origin, and it spins up a disposable worktree, runs an AI-driven validation pipeline, forwards the branch to the configured push target only after every check passes, and opens a clean PR automatically.
Autonomous Security for the AI Era.
Open-source AI hackers to find and fix your app’s vulnerabilities. Strix are autonomous AI agents that act just like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proof-of-concepts. Built for developers and security teams who need fast, accurate security testing without the overhead of manual pentesting or the false positives of static analysis tools.
Related contents:
VS Code extension for LLM-assisted code/text completion.
Local LLM-assisted text completion, chat with AI and agentic coding extension for VS Code.
Related contents:
Autonomous, multi-agent AI research — a PhD's workflow on a single-GPU budget.
An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination.
ScholarLoop runs the loop a PhD actually runs: it reads the literature, forms a grounded hypothesis, runs real ML experiments, scores them against a frozen ground-truth metric, learns from its failures, and drafts a peer-reviewed write-up — autonomously, with a deterministic harness that keeps the agents honest and impossible to reward-hack.
Pipeline-parallel LLM inference across GPUs on separate machines.
Pipeline-parallel LLM inference across GPUs on separate machines. A model too large for any single card is split into contiguous blocks of layers — one shard per GPU — and a request is served by streaming activations through the shards in order. No datacenter, no single host, and no node ever holds the whole model.
VS Code chat sidebar for local AI coding agents.
A VS Code chat sidebar that connects your editor to local AI coding agents.