apache2-licensed
Swift, in the browser.
Run declarative Swift applications natively in the browser with WebAssembly.
Personal tutoring, reimagined.
Agent-native Learning Companion that grows with you. Fully Open-Sourced.
A community-driven Matrix homeserver. Fast, lightweight and open.
Related contents:
Self-hosted SSH & SFTP browser workspace.
Security-focused, self-hosted SSH and SFTP workspace for homelabs and teams - multi-user, passkeys, OIDC, encrypted keys, backups, and offline-ready. WebSSH is a free, open-source SSH and SFTP client you host yourself. Open terminals, move files and manage remote servers from your browser.
The next era of web interfaces. Built in Rust.
An extremely performant, batteries-included Rust web framework built around a new programming model for composable, multi-target rendering.
Proa is building the next generation of interface infrastructure for the web. It enables you to create extremely fast, scalable applications and services in Rust by bringing compiled components, streaming, data loading, and fine-grained interactive islands into one framework.
Related contents:
A wiki connected to the systems it describes. Self-Hosted Wiki With Live Metric Charts.
Oxynote is an open-source workspace for engineering docs. Text, diagrams and live metrics in one editor, with a diff for every change.
Fast, programmable git infrastructure on object storage. git infrastructure for agentic workloads.
Programmable git infrastructure on top of object storage. Think turbopuffer for git. Open source alternative to Pierre (code.storage) and Cloudflare Artifacts.
Thousands of pushes per second, open-source and APIs built for machines. Build scalable CI, work with thousands of agents in parallel or embed git version control into your product.
the agentic IDE that gets better every time you use it.
Vibe code with pi in a lightweight, real IDE that customises itself around the way you work — The Vibe You Need.
ThinkRail is the agentic IDE that gets better every time you use it — learning your project through living specs today, and building its own capabilities tomorrow.
Free .docx to .md Converter.
Convert Word (.docx) files to clean Markdown, entirely in your browser. Your files are never uploaded.
Related contents:
Your AI agent running your server. Under Control.
Open source. Self-hosted. Easy for anyone, not just sysadmins. The easiest way to self-host projects on your own server. Connect your AI agent and let it deploy, maintain and manage multiple projects on any stack, while keeping your server organized and under control. Easy for anyone, not just sysadmins.
Next generation toolkit for web3D and photorealistic graphics.
Threepipe is a modern 3D framework built on top of three.js, written in TypeScript, designed to make creating high-quality, modular, and extensible 3D experiences on the web simple and enjoyable.
Your next app. Built in Python. Build cross-platform apps in Python .
Build beautiful web, desktop, and mobile apps from one Python codebase. Flet is a Python framework for building web, desktop, and mobile apps without prior experience in frontend development.
The open-source alternative to Claude Managed Agents.
The open-source managed agent platform. A self-hostable alternative to Claude Managed Agents and OpenAI's Agents API.
Omnara is an open-source managed agent platform. Use the API to run AI agents on any model and any machine, with tools, secrets, permissions, and streaming built in. Self-host it for free under Apache 2.0, or use Omnara Cloud.
Recursive Agent Harnessing for an Open World .
A harness is the system around a model that enables it to act as an agent: prompts, tools, memory, skills, orchestration, and more. Harnessing is the process of optimizing that system.
Harness² is a plug-and-play framework for recursive agent harnessing in an open world, where agents encounter tasks unseen during harness design. It connects two levels of recursion while keeping model weights fixed:
Any software. Any codebase. Any Web API. Generate an agent-native CLI and let AI agents operate it — install with a single command.
The refactorable warehouse Verify early, test properly, and refactor safely.
SQL transformation framework with custom compile-time checks, end-to-end testing and safe renames that keep your table history.
Change your warehouse as often as your code. SQLBuild brings compile-time checks, E2E tests and safe renames to your SQL, so change stops being risky.
Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first. A maintained fork of Capital One's VulnHunter, rebuilt for any agent harness.
⚡ Energy consumption metrology agent. Let "scaph" dive and bring back the metrics that will help you make your systems and applications more sustainable !
Scaphandre [skafɑ̃dʁ] is a metrology agent dedicated to electric power and energy consumption metrics. The goal of the project is to permit to any company or individual to measure the power consumption of its tech services and get this data in a convenient form, sending it through any monitoring or data analysis toolchain.
Enterprise AI Gateway Built for Scale.
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.
A K9s-inspired terminal UI for Flux resources, controller health, and GitOps state.
Related contents:
AWS Cost Estimation and Optimization.
Open-source policy engine that blocks bad AWS spending patterns before they ship and remediates what's already burning.
Deep memory for agents over large datasets. Index any table, export or log once; your agent gets the few records that answer the question.
Deep memory for agents over large datasets. Leviathan is a single static binary that turns your records (JSONL, JSON, CSV/TSV, SQLite, or anything a database CLI can export) into a ranked full-text index.
API Mocking and Testing.
The open source, cloud native tool for API Mocking and Testing Microcks leverages API standards to provide a uniform and multi-protocol approach, empowering your API and microservices lifecycle. It strengthens your ecosystem to create an adaptable API value chain.
Related contents:
Manila is the OpenStack Shared Filesystems service for providing Shared Filesystems as a service.
Related contents:
Oak is version control built for people and agents working together.
What are the odds git is the fastest way for agents to work? We don't think it is, so we're building something that is. In our benchmarks, snapshots and status checks run up to 95% faster than git. You don't have to change your model or your IDE. Just tell your agents to use Oak.
Run AI agents from YAML, like containers.
Docker Agent is to AI agents what docker run is to containers. Define an agent in a YAML file, run it with one command, share it through any OCI registry — the same workflow you already use for images.
Isolated VM environments for running Claude Code, Codex, and Grok Build.
coop is a Rust CLI that manages disposable virtual machines where Claude Code, Codex, and Grok Build have full tool access: Docker, git, compilers, package managers, all without risk to your host machine. Each VM is isolated, reproducible, and cheap to create and destroy.
Open a million-key database without the spinner. Native Redis GUI for large keyspaces.
GPU-drawn UI and virtual-scrolled SCAN — browse huge keyspaces, decode real payloads, and stay safe on production. Not another Electron client.
Related contents:
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Multilingual, non-autoregressive System 1 decision model. Give it a state (text, email, ticket, or JSON) and typed questions; it returns typed answers with mathematically calibrated probabilities in a single forward pass (~33 ms) across 100+ languages. Trained with reinforcement learning against strictly proper scoring rules (RLCD), so reporting honest probabilities is the only way to maximise reward. It never generates text, so there is nothing to parse and nothing to hallucinate.
Related contents:
Rebalancer is a domain-specific language and tool for specifying and solving assignment problems (eg, putting balls in boxes with complex rules).
Rebalancer is a framework for specifying, solving, and debugging assignment problems: deciding how to place objects into containers so that the result satisfies your constraints and optimizes your objectives. Instead of hand-writing a mathematical model, you describe the problem once with a high-level, reusable domain-specific language (DSL), let Rebalancer's solvers find an assignment, and inspect the result to understand why it came out the way it did.
Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.
The Open-Source Charting Core by LuxAlgo.
Fast, extensible financial charts for the web. The open-source core of Vela by LuxAlgo.
The open source AI testing framework. Next generation e2e testing framework for web and mobile apps.
e2e is an end-to-end testing framework for web and mobile apps. Describe a goal in natural language and an agent drives the app to reach it. Check the result with locators and assertions in the same test.
Find the noisy neighbors on a shared Kubernetes cluster: which tenants take more than they asked for, and who is exposed to them.
A kubectl plugin for shared Kubernetes clusters. It names the tenants using more than they asked for, and the tenants on the same node exposed to them.
It uses data every cluster already has. No Prometheus, no agent, no CRDs: one read-only binary.
See how a Parquet file is laid out, byte by byte. Only the footer and indexes are downloaded.
See how a Parquet file is laid out on disk: row groups, column chunks, pages, indexes, bloom filters and the footer.
Paste a Hub URL, an hf:// path, any URL that allows CORS range requests, or open a local file. Only the footer and page indexes are downloaded, so a 2 GB file opens after reading about 3 MB. Parsing uses hyparquet.
A personal reading tracker with a bold editorial look. Books carry ratings, reading dates, and their own notes pages, and can wear real cover photos — searched from a catalogue, uploaded, or pasted straight from the clipboard. A vocabulary registry keeps the words learned along the way.
Bookplate is self-hosted: you run it on your own machine or server with Docker, and your library never leaves it. Everything can be exported at any time as a zip of plain JSON, markdown and image files.
Intelligent model router for coding agents.
Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.
25 MB lightweight cross-platform database client for 100+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker.
TUI for MongoDB.
MongoDB TUI manager designed to simplify data visualization and quick manipulation.
A fast and efficient CLI tool for MongoDB database management, designed for developers who love to work in the terminal.
An LLM Gateway which optimises your token usage.
Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.
Doltgres is Dolt for Postgres Database version control in Postgres-flavored SQL.
Git versions file, Doltgres versions tables. It's like Git and Postgres had a baby.
Protobuf RPC that works.
Connect is a family of libraries for building browser and gRPC-compatible APIs. If you’re tired of hand-written boilerplate and turned off by massive frameworks, Connect is for you.
Related contents:
DevSecOps XL Labs CLI.
Turn declarative exercises into reproducible, runnable and verifiable lab environments.
dsoxlab turns declarative exercises into reproducible, runnable and verifiable environments. A catalog states what it offers through a root meta.yml and one lab.yaml per lab; the engine provisions what each lab asks for, opens it, and proves the result with tests that read the state of the system rather than the commands typed into it.
OpenShell is the safe, private runtime for autonomous AI agents.
NVIDIA OpenShell is an open-source runtime for executing fleets of autonomous AI agents in sandboxed environments with kernel-level isolation. It combines sandbox runtime controls and a declarative YAML policy so teams can run agents without giving them unrestricted access to local files, credentials, and external networks.
A tool for writing better scripts.
Bash is great, but when it comes to writing more complex scripts, many people prefer a more convenient programming language. JavaScript is a perfect choice, but the Node.js standard library requires additional hassle before using. No compromise, take the best of both. The zx package provides useful cross-platform wrappers around child_process, escapes arguments and gives sensible defaults.
Related contents:
Forge is a schema-first OpenAPI code generation and surface tooling framework. It provides a plugin-based architecture for resolving OpenAPI 3.x specifications, applying JSONPath-based overlays, and generating typed SDKs, CLI interfaces, runtime helpers, and documentation.
Related contents:
The Open Source Integration Framework
Connect anything. Route everything. 350+ connectors, written in Java, YAML, or XML, deployed on Spring Boot, Quarkus, or standalone with the Camel CLI.
Apache Camel is an open source integration framework with 350+ connectors for databases, APIs, message brokers, and cloud services. Write routes in Java, YAML, or XML. Run on Spring Boot, Quarkus, or standalone with the Camel CLI. In production since 2007 — used by thousands of companies worldwide. Apache License 2.0.
Related contents:
Talk to one agent. Build with a whole team. Multi-agent harness that runs Claude Code and Codex together as one system.
Bring your ideas and feedback to a lead agent. It delegates to specialists, tracks their work and brings answers back to you. OpenRig lets Claude Code, Codex and Pi work together on projects that take weeks or months.
Build fantastic, high-performance desktop apps.
A production-ready Rust UI framework with 75+ components and primitives, WebAssembly, accessibility, UI integration testing, data tables, docking, charts, code editing, and JavaScript extensions.
The open source, cloud-native harness.
Build and run capable agents with the same platform patterns you use for the rest of your software. Built from the ground up to run in the cloud. Get your harness off your laptop and run fleets of agents anywhere.
Open source agent harness, built from the ground up for cloud-native production workloads on infrastructure you control. Run the same provider-agnostic loop locally, remotely, or on Kubernetes, with durable state, permissions, and gRPC/HTTP-SSE APIs.
Drop sandbox for Linux. Linux sandboxing that doesn’t get in your way.
Isolate programs and coding agents without leaving your familiar work environment. Drop allows you to easily create sandboxed environments that isolate programs and coding agents while preserving as many aspects of your work environment as possible. Drop uses your existing distribution, so all the programs you've installed are available in the sandbox. Your username is preserved, and selected configuration files remain readable in the sandbox.
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
Open source SDK for AI agents in Python and TypeScript. A model-driven approach to building AI agents in just a few lines of code.
Strands Agents is an open-source SDK for building and running AI agents in Python and TypeScript. Choose Strands when you would otherwise write your own agent loop: it runs in your process with no hosted control plane, and it covers the jobs a hand-rolled loop grows into. In one SDK you get lifecycle controls (turn limits, token budgets, cancellation, stop reasons), tools and structured output, MCP, multi-agent patterns, memory and sessions, model portability, streaming, guardrails, tracing, and evals.
Make GPU Sharing Flexible and Easy . Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond.
kvcached (KV cache daemon) is a KV cache library for LLM serving/training on shared GPUs. By bringing OS-style virtual memory abstraction to LLM systems, it enables elastic and demand-driven KV cache allocation, improving GPU utilization under dynamic workloads.
The LLM Red Teaming Framework
Brought to you by the team behind DeepEval, DeepTeam enables teams to red team any AI application — surfacing vulnerabilities, jailbreaks, and agentic risks before attackers do.
tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own.
One call. not ten reads. code intelligence for your AI coding agent.
Gortex indexes your repository into an in-memory knowledge graph and serves it to your coding agent over MCP, HTTP, and a web UI. One graph query replaces a stack of file reads — up to 50× fewer tokens per response. 257 languages, a 21-tool MCP surface, live editor-buffer overlays, speculative edits, dataflow, clone detection, graph-grounded PR review, and a 17-server LSP bridge. Built for 19 AI coding agents on macOS, Linux & Windows — one binary, zero services.
Knot is a platform for managing development environments, testing systems, automation workflows, and platform services across containers and virtual machines. Create, manage, and share everything from disposable sandboxes to long-running workloads through a single interface, whether running locally or across a cluster.
Rust Glancer is an experimental LSP implementation that tries to use a different architecture compared to rust-analyzer in order to lower RAM usage and make editor restarts faster.
Related contents:
Google's open agentic orchestrator. Declare an agentic task. AX runs it at scale.
AX sandboxes your task, wires up its workspace, fences its network, and helps you run billions of them per cluster. Either use a single task per agent, or compose as many as your agent needs.