apache2-licensed
Switchyard is a Rust proxy and library for LLM traffic. It routes requests across providers, translates between OpenAI and Anthropic APIs, records operational metrics, and provides typed, composable routing algorithms.
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
Agent Skills for Google products and technologies
Self-Hosted Email Delivery & Inbound Platform.
Self-hosted email delivery platform that enables applications to send emails via HTTP APIs while handling SMTP delivery, templates, storage, security, and analytics. Fully self-hostable alternative to services like SendGrid or Mailgun.
How PostgreSQL Works, in 3D.
PGSimCity is an independent, non-commercial educational visualization of PostgreSQL internals. It is not affiliated with, sponsored, endorsed, or approved by Electronic Arts Inc. SimCity is a trademark of Electronic Arts Inc.
Open Source Integration Layer for AI Agents. Add any integration in minutes.
Connect to the apps your users rely on without maintaining the infrastructure that keeps it working.
Corsair is the unified integration layer for your agents. Connect your Corsair instance to your agent and immediately get access to every integration. Your agent never sees the credentials, and you control exactly what it can do.
A Control Mechanism for AI Agent.
This document introduces .agentignore, a simple yet powerful way designed to give you precise control over which parts of your codebase AI agents and code assistants can access.
Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.
Ante is designed for cellular-native agents: like cells in an organism, tiny, expendable, massively replicated.
Local emulator for European cloud APIs — Scaleway, Outscale, Exoscale. One binary, one port, no account.
Helios offers verifiable online elections.
We believe democracy is important, whether it’s your book club, parent-teacher association, student government, workers’ union, or state. So we’ve made truly verifiable elections as easy as everything else on the Web.
Related contents:
A lightweight and high-performance reverse proxy for NAT traversal, written in Rust. An alternative to frp and ngrok.
rathole, like frp and ngrok, can help to expose the service on the device behind the NAT to the Internet, via a server with a public IP.
Context Engineering for AI Agents.
Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.
self-hosted, distributed Durable Objects.
celld is a stateful distributed system. It runs server-side JavaScript on your machines and keeps all shared data in an S3-compatible bucket that you own. The JavaScript API is the same API that Cloudflare Workers and Durable Objects supply.
Related contents:
A portable package format for reusable components that extend AI agents.
Agent Plugins is an open, vendor-neutral standard for packaging reusable components into portable plugins. Its version 1.0.0 specification defines a shared format for Agent Skills and MCP servers that compatible clients can discover and load consistently.
Related contents:
a beautiful JSON viewer for the web.
JSON Hero is an open-source, beautiful JSON explorer for the web that lets you browse, search and navigate your JSON files at speed. 🚀. Built with 💜 by the Trigger.dev team.
AI Memory Layer for your Agents & Apps.
Mem0 ("mem-zero") enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions. It remembers user preferences, adapts to individual needs, and continuously learns over time—ideal for customer support chatbots, AI assistants, and autonomous systems.
Local-first documentation for AI agents. Up-to-date docs for AI agents — local, instant, plug and play.
Context is an MCP server backed by a community-driven package registry with 100+ popular libraries already built and ready to use. When your AI agent needs documentation, it searches the registry, downloads the right package, and queries it locally — all automatically.
Related contents:
The Visual JSON Editor for Humans.
The Visual JSON Editor. Schema-aware, embeddable, extensible.
asago (AI Safety And Governance Orchestration) is an open-source community that aims to automate the journey from AI governance policy to production-ready, safely deployed AI systems — bridging the gap between compliance teams, AI engineers, and infrastructure operators.
Related contents:
Language server for Dockerfiles, Compose files, and Bake files.
The Docker Language Server is a language server for providing language features for file types in the Docker ecosystem (Dockerfiles, Compose files, and Bake files).
Sandboxes for every agent.
The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud. A Box is a hardware-isolated micro-VM that runs any OCI image — and it persists. Agents install packages, write files, and resume across turns, never from cold.
Sandbox for AI Agents — Kernel-Level Isolation.
Run AI agents in a zero latency sandbox in seconds and with zero setup — Claude Code, Codex, Pi, CoPilot, Hermes, OpenCode, OpenClaw and more — nono gets you up and running within seconds, with no daemon, no container, no VM, and no disk space usage. Out of the box, nono enforces a least-privilege sandbox and supports macOS, Linux, and Windows (WSL2).
Adds a /-/mcp MCP server to any Datasette instance.
Related contents:
CLI tool for exploring an MCP server.
Related contents:
ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
ADR (Agentic AI Detection and Response) is an enterprise security system for AI agents. It helps organizations secure employee-facing agents such as Cursor, Claude Code, and Codex, as well as customer-facing agents such as AI support agents.
The model IS the database. Query neural network weights like a graph database. No GPU required.
LARQL decompiles transformer models into a queryable format called a vindex (vector index), then provides LQL (Lazarus Query Language) to browse, edit, and recompile the model's knowledge.
A self-hosted email client with an AI agent, running entirely on Cloudflare Workers.
Agentic Inbox lets you send, receive, and manage emails through a modern web interface -- all powered by your own Cloudflare account. Incoming emails arrive via Cloudflare Email Routing, each mailbox is isolated in its own Durable Object with a SQLite database, and attachments are stored in R2.
Docker Model Runner (DMR) makes it easy to manage, run, and deploy AI models using Docker. Designed for developers, Docker Model Runner streamlines the process of pulling, running, and serving large language models (LLMs) and other AI models directly from Docker Hub, any OCI-compliant registry, or Hugging Face.
Related contents:
Make any TypeScript Function Durable.
use workflow brings durability, reliability, and observability to async JavaScript. Build apps and AI Agents that can suspend, resume, and maintain state with ease.
Related contents:
AI Agent for Snowflake.
An open-source, self-hosted agentic framework that turns plain English into Snowflake operations.
Frosty is a 153-agent system built by Gyrus Inc that lets you manage your entire Snowflake environment in plain English — from querying data to administering security policies.
A hook that registers a WebMCP tool with the browser and ties its lifecycle to a React component.
WebMCP lets a page expose JavaScript functions as "tools" that an AI agent (browser-built-in, iframe-hosted, or extension) can discover and call. The site author can expose functionality, and the agent uses this instead of scraping the DOM, a11y tree, or using screenshots.
Userspace macOS ARM64 → Linux aarch64 translation layer (CLI-first, no JIT).
Load Darwin Mach-O on Linux aarch64, map a freestanding libSystem, translate BSD syscalls, and run real guests (clang probes, 7-Zip 7zz, curl, threads).
An egress firewall for untrusted workloads.
iron-proxy is a single-binary egress firewall for workloads you don't fully trust. It enforces an allowlist on outbound HTTP and HTTPS, holds credentials so the workload never sees the real value, and records every request as structured JSON.
Utilities that should have been Terraform core functions.
Core functions with identical implementations for Terraform, OpenTofu, Terratest, and other software in the so-called Terra/Fu ecosystem.
While some of these can be implemented in HCL, some of them begin to push up against the limits of Terraform and the HCL2 configuration language. Exposing these functions as both a Go library as well as a Terraform/OpenTofu provider enables us to use the same functionality in both our Terraform/OpenTofu applies as well as while using a testing framework.
High-performance self-hosted personal dashboard. Single binary, premium UI, native grid engine in pure JavaScript.
Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.
numbat observes supported desktop, CLI, IDE, and gateway agents through local hooks and plugins, OTLP/HTTP logs, and on-disk session artifacts. Live and at-rest activity is normalized into one event model and evaluated by the same CEL rule engine. Detection runs locally; records can be written to stdout or a local file and optionally delivered over HTTP.
Gemma 4 26B-A4B inference in about 2 GB of RAM A custom Swift + Metal runtime for any Apple Silicon Mac, even the 8 GB ones.
A High-Performance Analytical Database.
The world's fastest open query engine for sub-second analytics both on and off the data lakehouse. With the flexibility to support nearly any scenario, StarRocks provides best-in-class performance for multi-dimensional analytics, real-time analytics, and ad-hoc queries. A Linux Foundation project.
the open standard for sealing anything.
The open standard for proving any file is real, unaltered, sealed by a known certificate, and in existence by a certain date. One standard for every kind of file: documents, images, email, code, containers. Verifiable by anyone, forever. The proof travels with the file and stands on its own.
TypeScript-to-Native Compiler.
Zero-runtime TypeScript. scriptc compiles ordinary TypeScript into small, fast native executables — no Node, no V8, no JavaScript engine in the binary.
No changes to your code. No annotations, no dialect — the same TypeScript you run on Node, type-checked by the real TypeScript compiler and compiled to native. What compiles behaves byte-for-byte like Node.
Related contents:
The framework for building agents
Like Next.js for agents. Build durable agents with one folder. eve is a filesystem-first framework for durable AI agents. Core agent capabilities live in conventional locations, so projects are easier to inspect, extend, and operate.
Related contents:
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.
SQL powered operating system instrumentation, monitoring, and analytics. Easily ask questions about your Linux, Windows, and macOS infrastructure.
osquery is an operating system instrumentation framework for Windows, OS X (macOS), and Linux. The tools make low-level operating system analytics and monitoring both performant and intuitive.
osquery exposes an operating system as a high-performance relational database. This allows you to write SQL queries to explore operating system data. With osquery, SQL tables represent abstract concepts such as running processes, loaded kernel modules, open network connections, browser plugins, hardware events or file hashes.
Related contents:
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 744-billion-parameter mind, on your desk tiny engine, immense model.
Run GLM-5.2 — 744B Mixture-of-Experts — on hardware you already own. Pure C, zero dependencies, experts staged just-in-time across VRAM, RAM and disk. The galaxy behind this text is real: the model's measured expert atlas.
Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.
Your people, your agents, your project — all in one place. A hive mind communication platform.
Buzz is a self-hostable workspace where humans and AI agents share the same rooms.
A Buzz community is the workspace a user reaches by URL. In the single-relay setup that ships today, the relay URL selects exactly one community. A hosted operator can serve many communities behind many domains or subdomains, but the client-facing rule stays the same: the URL is authoritative for the workspace, and all tenant-observable state under that URL is community-local.
Related contents:
Headless iOS Simulator manager/farm + host-side input injection for iOS 26 — taps, swipes, multi-finger gestures, and 60 fps streaming .
A single Swift CLI — baguette — plus a self-contained web UI that gives you full headless control of an iOS simulator without opening Xcode or Simulator.app. Boot devices, stream their screens at 60 fps, dispatch taps / swipes / multi-finger gestures / system gestures / keyboard / hardware buttons, tail the unified log, inspect the accessibility tree, take screenshots and recordings, and — as of 0.1.72 — pipe your Mac webcam into the simulator's camera APIs.
A calm, CLI-native way to semantically grep everything, like code, images, pdfs and more.
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).
Redis-compatible distributed cache.
A low-latency, high-throughput, distributed cache. Drop-in replacement for Redis — up to 1.9x faster with p99 latency under 1.3ms.
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.
Network Observability for the AI Era.
eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Open Source, Self-Hostable Deployment Platform.
Push your code - builds, config, and deployment are handled automatically. Use our cloud or connect your own servers. Zero lock‑in, completely open‑source.
Open-source, self-hostable deployment platform with built-in CI/CD. Push code, ship containers, manage infrastructure — from a desktop app, web dashboard, or CLI.
A top for eBPF programs.real-time view of running eBPF programs.
Real-time average runtime per call, events/s, and CPU utilization for every loaded eBPF program.
Keep your Docker containers fresh, safely. A safe Docker container auto-updater.
freshdock watches your running containers, notices when a newer image ships, and updates them health-gated. A broken update rolls back automatically instead of leaving you with a dead service. The maintained successor to the archived Watchtower.
Schedule, supervise, observe. One binary.
Cron job manager + process supervisor in a single binary. Web dashboard, TUI, retries, failure notifications. crond/supervisord replacement
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.
The lazygit for PostgreSQL. A vim-style terminal UI for browsing, querying, and editing your database without leaving the keyboard.
A vim-style TUI PostgreSQL client built like lazygit — fast keyboard navigation, modal panes, and a focused workflow for browsing and querying your database from the terminal.
An open source Snowflake cost optimization and observability dashboard.
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.