mit-licensed
A vector indexing library to bring fast, fresh and filtered search to your database.
DiskANN3 is a composable library for bringing scalable, accurate and cost-effective vector indexing to multiple databases. It draws on research from the DiskANN project.
Related contents:
The app people use to manage AI agents for work.
Open-source orchestration for teams of AI agents.
If OpenClaw is an employee, Paperclip is the company.
Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Bring your own agents, assign goals, and track work and costs from one dashboard.
AI-Powered Codebase Analysis.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs.
Code-Graph-RAG parses a multi-language codebase with Tree-sitter, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.
Morph any SVG icon into any other. SVG icon morphing library for React, Vue & Svelte.
Animate Lucide, Tabler, Heroicons or any stroke icon set. Optimal rotation solved in closed form, spring physics, zero dependencies.
Related contents:
Sound effects for the interface, performed live.
Foley is a tiny, dependency-free library of 28 interaction sounds, synthesized live with Web Audio the instant you interact — no audio files, no setup. When the defaults aren’t yours, redesign them and ship a sound set: your product’s sonic identity in one small JSON file.
Related contents:
Write Native with TypeScript.
Render native platform UI with direct access to native APIs automatically backed by TypeScript. ⚡ Write Native with TypeScript ✨ Best of all worlds (TypeScript, Swift, Objective C, Kotlin, Java, Dart). Use what you love ❤️ Angular, React, Solid, Svelte, Vue with: iOS (UIKit, SwiftUI), Android (View, Jetpack Compose), Flutter and you name it compatible.
NativeScript empowers you to access native APIs from JavaScript directly. Currently iOS, Android, and visionOS runtimes are provided for rich mobile development across a variety of diverse use cases.
Related contents:
Inferno is an insanely fast, React-like library for building high-performance user interfaces on both the client and server.
The main objective of the InfernoJS project is to provide the fastest possible runtime performance for web applications. Inferno excels at rendering real time data views or large DOM trees.
Related contents:
the elegant TypeScript UI framework.
Ripple is a TypeScript-first UI framework built around .tsrx files, fine-grained reactivity, scoped styles, and a small runtime. It pairs the authoring feel of JSX with template-native control flow and TypeScript setup that can live right beside the UI it feeds.
Related contents:
Agentic Development Environment for AI Coding. Desktop and web interface for OpenCode AI agent.
OpenChamber is an open-source workspace for running, supervising, and reviewing AI coding work across desktop, browser, editor, and mobile.
OpenChamber gives you one place to direct agent work, understand the changes, and move them toward release. Your projects stay available when you switch devices or step away.
Local memory for AI agents.
Link gives Codex, Claude, Cursor, Kiro, VS Code, Copilot, Antigravity, and other local agents the same source-backed memory, stored locally as Markdown.
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Prime Agent is an open-source coding and research agent for general and long-running work.
Related contents:
Open-Source Kubernetes Desktop Client Built in Rust. The Kubernetes control room for engineers and AI agents.
Investigate, analyse, and take safe action across Kubernetes clusters from one local-first desktop workspace, built with a pure-Rust core. Backend capabilities are also available to AI agents through MCP.
A terminal user interface (TUI) for GitLab/GitHub, built on top of glab/gh. Browse issues, merge requests, pipelines, runners, and releases without leaving your terminal. Built for personal use.
Webhooks as a Service – Secure and Enterprise Ready. Webhooks your customers can actually rely on. Ship webhooks in days, not quarters, using the Svix webhooks service. Customer-facing UI, retries, idempotency, security, observability, and more built in.
Svix makes it easy for developers to send webhooks. Developers make one API call, and Svix takes care of deliverability, retries, security, and more. For more information, please refer to the Svix homepage.
a PHP language server .
Fast PHP language server with deep type intelligence. Generics, Laravel, PHPStan annotations. Ready in an instant.
Lightweight Network Scanner.
LAN Orangutan is a lightweight network scanner with persistent device labeling, multi-network support, and Tailscale integration. Built by 291 Group.
🧯 A tiny qBittorrent CLI for people who don't want to nuke their seedbox by accident.
Inspect torrents and trackers, diagnose problems, and preview bulk changes before they reach qBittorrent.
A keyboard-first, self-hosted bookmark dashboard. No accounts, no cloud, no noise.
A dashboard where every widget is a function.
No query builder, no plugin format, no YAML dialect to learn. A widget is a TypeScript file on disk that returns data. The platform runs it on a schedule, on an MQTT message or on a webhook, checks what came back against a typed schema, and pushes it to every open tab.
the IDE for loop-driven development.
bb is an agentic IDE that can control itself. You can seamlessly orchestrate all of your favorite coding agents together and have them programmatically use bb too.
Related contents:
The local control plane for long-running AI agent work.
A lightweight state kernel and agent-agnostic local control plane for loop engineering, LoopX keeps long-running work reviewable, restartable, and easier to hand off across turns, tools, and agents. It does not replace your agent runtime.
Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executable todos, evidence logs, and verifiable handoffs.
The open-source SDK for bringing any agent into any chat platform: Slack, Microsoft Teams, Discord, Telegram - with native, Interactive UI.
Risk analysis, from inherent to residual. the standalone, offline risk-analysis editor.
A standalone risk-analysis editor, built on a generic, configurable model: define your grid, enter risks and controls, and visualize the shift from inherent to residual risk – matrices, trajectories, action plan and report. The whole analysis fits in a single open .rae.json file.
Kit is a powerful, extensible AI coding agent CLI with multi-provider support, built-in tools, and a rich extension system.
MCP, made portable.
mcporter is a TypeScript runtime, CLI, and code-generation toolkit for the Model Context Protocol — built so AI agents and developers can call any MCP server without boilerplate.
The smallest vector index in the world. RAG Everything with LEANN!
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
LEANN is an innovative vector database that democratizes personal AI. Transform your laptop into a powerful RAG system that can index and search through millions of documents while using 97% less storage than traditional solutions without accuracy loss.
An unfaithful port of Linq to Sql to Typescript.
A type-safe query builder for TypeScript. Queries are expressed as inline arrow functions, parsed into an expression tree, and compiled into SQL for PostgreSQL or SQLite. The API is similar to DotNet's LINQ-based frameworks.
The Package Manager forAI Agent Skills. The Universal Skill Manager for AI Agents
Install, share, and discover skills for Claude, Cursor, Copilot, and more. Like npm, but for AI coding assistants.
The CLI for the open agent skills ecosystem. npx skills.
An Active Directory security-assessment toolkit in Rust: a PingCastle-class auditor that maps a domain's attack paths — scored, graphed, and MITRE-tagged — then, for authorized red-team and research use, proves those paths end-to-end. One static binary, from Kali/Linux or Windows, on an embedded from-scratch DCE/RPC · NTLM · SMB2 · Kerberos stack (the "impacket for Rust" that didn't otherwise exist).
Free email OSINT tool, 2500+ platforms, identity clustering, breach detection. No API keys required.
Self-hostable OSINT platform for investigating email addresses. Fan out across breach databases, social networks, DNS records, and the open web — get back a unified exposure score and structured findings you can export or pipe into Maltego.
Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs.
Focused guard skills for coding agents: second-pass quality gates that catch the systematic failure modes of AI-generated code, tests, and docs before they ship.
Best use: let your agent do the work, then invoke the relevant guard on the diff before you present, commit, or merge it. These skills can guide writing when you explicitly ask for that, but they are strongest as reactive review passes.
Rules for writing code that coding agents (and humans) can find through plain-text search: distinctive names, precise types, comments where search lands, and concept-named modules.
Related contents:
codebase intelligence for typescript and javascript.
AI made writing code fast. Keeping a codebase coherent is now the hard part. Fallow finds what is unused, duplicated, overly complex, or drifting across boundaries, and can add the one thing static tools cannot: what actually runs in production.
Related contents:
A language server for Caddyfile configuration files.
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
Compiler-First Reactive UI. Write JavaScript. Get reactivity for free.
A compiler-first UI framework that turns ordinary classes and functions into surgical DOM updates. No virtual DOM. No hooks. No signals. Just your code — wired at build time.
Related contents:
A library for building dynamic webapps, using Js_of_ocaml.
Bonsai is a UI library for building performant, reactive web applications in OCaml, partly inspired by Elm. It is used to build almost all web applications inside Jane Street, everything from the corporate directory to tools that monitor and interact with our trading systems. A simple Bonsai component with a little interactivity looks like this:
Local analytics dashboard for Claude Code. No cloud, no telemetry.
Related contents:
Ecosystem, Frameworks, Workflows for AI coding agents.
Gentle-AI is NOT an AI agent installer. Most agents are easy to install. It is an ecosystem configurator that equips the AI coding agent(s) you already use with persistent memory, Spec-Driven Development (SDD), curated skills, MCP servers, model routing, a teaching-oriented persona, and bounded native review.
Before: "I installed Claude Code / OpenCode / Cursor, but it's just a chatbot that writes code."
After: Your agent now has memory, skills, workflow, MCP tools, and a persona that actually teaches you.
Related contents:
Kubernetes GitOps with nix and Argo CD.
Managing Kubernetes configurations at scale is hard. Helm charts require complex value overrides, Kustomize leads to repetitive overlays, and raw YAML becomes unmaintainable. Reviewing changes across environments is nearly impossible.
Nixidy solves this by bringing the power of Nix and the NixOS module system to Kubernetes.
Related contents:
Free Tinkercad Alternative. Forge ideas into 3D,right in your browser A local-first 3D design editor that runs in your browser.
Shape, combine, refine, import, and export models in one focused workspace. No account or payment required.
A Laravel database analysis tool that inspects schema structure, indexes, and constraints to identify potential issues and enforce best practices.
The DBStan package provides detailed analysis and insights into your database schema for Laravel applications.
It helps identify structural issues, missing indexes, normalization problems, nullable column risks, foreign key inconsistencies, and performance concerns. It is an essential tool for debugging, optimizing, reviewing, and maintaining a healthy database architecture in Laravel projects.
On-device models that know when they're wrong: every answer carries a confidence score for cloud handoff.
A small, on-device model is fast and private, but sometimes wrong. At Cactus we post-train models to know when they are wrong: we ship probes inside the checkpoint that score every answer with a confidence between 0 and 1, returned as structured data (never parsed out of the answer text). Answer on-device when confidence is high; you can re-route to a bigger model when it's low:
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm.
DwarfStar is a small native inference engine optimized first for DeepSeek V4 Flash. It also supports GLM 5.2 and, on very high-memory machines, DeepSeek V4 PRO. It is self-contained and deliberately narrow, not a general GGUF runner. Model loading, prompt rendering, tool calls, KV state, the HTTP server, and the coding agent are built and tested together. The repository also includes tools and data for GGUF, imatrix, quality, and speed.
Use stacked pull requests to break large code changes into a chain of smaller, dependent pull requests you can review and merge independently.
Predictive inline shell autosuggestions for zsh - Go daemon, no TUI, no sync. smarter than history, lighter than a plugin.
Deja is a smarter replacement for zsh-autosuggestions. Instead of only surfacing commands that start with what you've typed, Deja uses fuzzy matching, directory awareness, and command sequence prediction to suggest what you actually want to run — as inline ghost text, after every keystroke, with zero latency.
Related contents:
Unlimited OCR Works. Welcome the Era of One-shot Long-horizon Parsing.
Create, calculate, and format money safely
An immutable library for expressing monetary values in JavaScript and TypeScript.
Money is complex, and the primitives of the language aren't enough to properly represent it. Dinero.js is a JavaScript library that lets you express monetary values, but also perform mutations, conversions, comparisons, formatting, and overall make money manipulation easier and safer in your application.
Self-hosted video library & downloader.
Self-hosted downloader and player for YouTube, Bilibili, Twitch, MissAV, and yt-dlp sites. Features channel subscriptions, auto-downloads, and local storage for media. Organize your library into collections with a sleek UI. Includes built-in Cloudflare Tunnel support for secure remote access without port forwarding. Docker-ready deployment.
Local PDF & Markdown knowledge base with semantic search and AI-powered enrichment.
Works with PDFs AND Markdown files - Index your research papers, books, notes, docs, and any .md files in one unified, searchable knowledge base.
AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,000+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.
Agent-driven research knowledge base. Agents collect, search, and synthesize web research into a persistent, searchable wiki.
Hyperresearch turns Claude Code into a deep research agent: one that currently leads the DeepResearch-Bench RACE leaderboard (benchmarked internally). A tier-adaptive 16-step pipeline takes one prompt and produces an adversarially-audited report with full source provenance. Every source it reads lands in a persistent, searchable vault, so each session starts smarter than the last.
A Terminal UI for Terraform Plans.
An interactive terminal UI for reading Terraform plans. A Terraform configuration is a graph, and a plan is a proposed change over that graph. Scrolling through hundrends of lines of terraform plan output makes that structure almost impossible to see. tfplantui renders the plan as its dependency graph — laid out in columns by dependency depth — and lets you walk it with the arrow keys, expanding any resource to see a color-coded before → after diff of its attributes.
Open-source, native Postgres GUI for macOS. Ask questions in English; review the SQL before it runs.
Postgres GUI using the LLM already on your Mac. Free, open-source native macOS database GUI using Apple's on-device Foundation Model for text-to-sql.
zeedumper connects to a Kubernetes cluster using your kubeconfig and dumps component z-pages — flagz, statusz, and configz — retrieving them through the API server proxy. The only credentials in play are those in your kubeconfig; the tool is read-only and never mutates the cluster.
It presents the results as structured text, JSON, or a self-contained HTML page.
📈 A small, fast chart for time series, lines, areas, ohlc & bars.
uPlot is a fast, memory-efficient Canvas 2D-based chart for plotting time series, lines, areas, ohlc & bars. From a cold start it can create an interactive chart containing 166,650 data points in 25ms, scaling linearly at ~100,000 pts/ms afterwards. In addition to fast initial render, the zooming and cursor performance is by far the best of any similar charting lib; at ~50 KB, it's likely the smallest and fastest time series plotter that doesn't make use of context-limited WebGL shaders or WASM, both of which have much higher startup cost and code size.
Terminal UIs on a Native Zig Core. OpenTUI is a library for building terminal user interfaces (TUIs).
Build rich, interactive terminal interfaces with TypeScript bindings, first-class React/Solid support, and a C ABI for any language.
Related contents:
MCP Server for kubernetes management commands.
MCP Server that can connect to a Kubernetes cluster and manage it. Supports loading kubeconfig from multiple sources in priority order.
Related contents: