The tools directory
Every tool that made an issue — 64 so far, four more each week. What it does, and whether it's worth your time.
agents
- Agent Governance Toolkit open source Microsoft's policy enforcement, agent identity, sandboxing, and audit layer for autonomous agents — one pip install, any framework. It intercepts tool calls and delegations before execution with deterministic fail-closed controls, and claims coverage of all ten OWASP Agentic risks. Python, TypeScript/.NET, Rust, and Go.
- AX open source Google's open orchestration runtime for agent workloads, in the Kubernetes idiom: you declare a Task and a Workspace in YAML — the git repos, MCP servers, and skills an agent needs — and AX runs it in a sandbox with CPU and memory limits, suspends it while it waits on a model, and resumes it in under a second. The part that matters this week is the Gateway: outbound traffic locked to an explicit allowlist of hosts and ports, with credentials injected at the edge rather than handed to the agent. Apache-2.0, written in Go.
- Cloudflare Security Audit Skill open source The MIT-licensed skill behind Cloudflare's internal fleet-wide vulnerability harness, installable into Claude Code or any skills-compatible agent with one `npx skills add`. It structures an audit as six phases — reconnaissance, coverage-led hunting by isolated hunter agents, adversarial validation by fresh verifier agents that never saw the hunt, schema-validated findings, independent re-verification, and a target-neutral report. Cloudflare's own funnel numbers: 20,799 raw candidates filtered to 12,057 validated and 7,245 findings engineering teams actually acted on.
- CubeSandbox open source Instant concurrent sandbox for AI agents -- lightweight, secure, purpose-built for agent code execution.
- DeepSeek Harness (dsh) open source DeepSeek's own agent harness, MIT, built on Cordis and organised so that everything — including the desktop and the Web UI — is a plugin. `npx @deepseek-ai/dsh web` starts a local server on 127.0.0.1:3080 and opens it; the README labels the whole thing a developer preview and warns in capitals that compatibility-breaking changes are coming.
- herdr open source Agent multiplexer for your terminal — run and juggle several AI agents in parallel (12K stars).
- OpenExecutive open source An open-source virtual executive team: one coherent executive persona backed by eight specialist Claude agents — strategy, finance, HR, legal, operations, marketing, product, and board communications — with episodic memory in SQLite, a ChromaDB vector store, and interfaces for web, Slack, email, Telegram, Discord, and the CLI. Apache 2.0, FastAPI plus Next.js; clone it, add an `ANTHROPIC_API_KEY`, and `make dev` puts the corner office on localhost:3000.
- orca open source Desktop environment for running multiple AI coding agents in parallel, on your own subscriptions.
- Page Agent open source Alibaba JavaScript in-page GUI agent that controls web interfaces with natural language.
- pi open source Unified agent toolkit: one LLM API across providers, an agent loop, a terminal UI, and a coding CLI — 80K stars and climbing.
- qm open source Multiplayer agent harness for teams, in Slack and on the web. Per-person and shared scopes each get their own memory, files, and permissions; runs Pi, OpenCode, Codex, or Claude Code underneath, self-hosted in your own cloud.
- reverse-skill open source A security-research skill router for coding agents: 40+ reverse-engineering, pentest, and CTF workflows with on-demand tool bootstrapping for Ghidra, Frida, IDA Pro, and radare2. Works with Claude Code, Cursor, Cline, and Kiro.
- strix open source Open-source AI pentesting agent — 37K stars — that probes your app for vulnerabilities before someone else does.
coding
- anti-slop open source Fifteen opinionated Oxlint rules that reject low-evidence TypeScript and JavaScript: chained type assertions, `unknown` parameters and returns, runtime `typeof` checks, module mocking, widen-then-assert. It is meant to be vendored rather than depended on — an agent skill copies the plugin in, merges the lint config, and then the files are yours to edit.
- Bend 2 open source Victor Taelin's parallel language, relaunched as 'a fast language that blocks AI mistakes via proof': Python-flavored syntax, a dependently-typed checker, and native compilation that runs the same binary on one core, sixteen, or the GPU. The AI angle is a LAWS.bend file — invariants your agent's code must prove before it can merge, with the checker as the reviewer that can't be sweet-talked. Apache-2.0, 21,000 stars, install by shell script.
- book-to-skill open source Converts technical books, PDFs, EPUBs, and document folders into structured agent skills — a SKILL.md mental model, chapter files loaded on demand, a glossary, and cheatsheets — for Claude Code, Copilot CLI, and Amp. Claims 24×–51× fewer tokens than dumping the book into context.
- codebase-memory-mcp open source Indexes your codebase into a persistent knowledge graph that agents query over MCP.
- Codex Plugin for Claude Code open source OpenAI plugin that lets you use Codex from inside Claude Code for code review and task delegation.
- Copperhead freemium 'Cursor for circuit boards': an agent that designs and verifies PCBs by editing KiCad files directly — schematic, layout, BOM — running electrical and design-rule checks through kicad-cli, keeping the docs in sync, and generating gerbers at the end. `npm i -g copperhead` and bring your own Claude or GPT key; the CLI is Apache 2.0 and free forever, the cloud tier is $49 a month and free for open hardware.
- design.md open source Google's format spec for describing visual identity and design rules to AI coding agents.
- Graphify open source Builds a searchable knowledge graph from any codebase; works across Claude Code, Codex, Cursor, and Gemini CLI.
- hallmark open source Anti-slop design skill for Claude Code, Cursor, and Codex. Anti-patterns, a slop-test gate, and twenty themes with distinct macrostructures — it refuses to ship generic UI.
- i-have-adhd open source A skill for coding agents — Claude Code and the rest — that forces ADHD-friendly output: the answer first, then numbered steps, no 'hope this helps' filler, no burying the fix in paragraph six. MIT-licensed pure instructions, installed by pasting one line into your CLI; the README's before/after examples make the case better than any pitch, and it ships translated into seven languages.
- Matt Pocock Skills open source A collection of composable agent skills for real engineering work — TDD, code review, debugging, domain modeling. Written to work across models, not just one vendor's CLI.
- no-mistakes open source An AI review gate that runs before code reaches the shared repo.
- Prime Agent open source A coding and research agent for long-running autonomous work, built on a Recursive Language Model — context as variables, subagents as function calls inside a persistent IPython REPL — plus a Continual Harness that keeps supplemental prompts, memories, and skills as durable state it refines with small evidence-backed updates.
- Stitch Skills open source Google-built library of design, build, and utility skills following the open Agent Skills standard — compatible with Claude Code, Cursor, and Codex via the Stitch MCP server.
models
- Jev paid TypeSafe AI's 'System One model' generates no text at all: you hand it structured program state and up to 255 options, and it returns a typed decision — classify, route, score, extract — with calibrated confidence, in 70 to 500 milliseconds. The pitch is replacing the small LLM calls buried inside pipelines, where parsing prose was always the bug. Pricing is $0.042 per million input tokens with output free; the catch is that it's a closed API behind an early-access waitlist.
- K2 Horizon open source A 'connected fleet' of six Apache-2.0 models from 0.9B to 375B parameters, out of the Institute of Foundation Models at Abu Dhabi's MBZUAI — the LLM360 lineage. The flagship is a 375B MoE with 23B active and 512K context; the 0.9B targets watches and glasses, the 3.7B and 7B target phones, and those small models ship the full stack — weights, training data, recipe, and code. Runs on vLLM, SGLang, and Ollama.
- Laya open source An open-weight 'System 1' decision engine: you pass it any state — an email, a ticket, a JSON document — plus typed questions (pick one of these, score this, yes or no), and it answers all of them in a single forward pass with calibrated confidence and no text generation at all. Under the hood are three small encoder checkpoints (ModernBERT-large for English, a 322M-parameter mmBERT for 100+ languages, and a fine-tuned one), with a router that picks per request. `pip install laya`, with optional extras for an MCP server, an HTTP server, LangChain, and ONNX. Apache-2.0.
- Strands Decider 2B open source A small open model that makes typed decisions — pick one, yes or no, rate it — with a confidence score, in one forward pass.
local AI
- Cactus Needle 3 freemium A foundation model for phones, wearables, and microcontrollers, built for automation rather than chat: tool calls, structured extraction, and embeddings. The trick is an 'intelligence ladder' — one set of weights where every depth from 2 to 20 layers is a usable model of its own, shipped as 2-bit binaries between roughly 9 and 29 MB — so you choose accuracy versus footprint per device without training a family. Open weights on Hugging Face under Apache-2.0; Cactus sells a one-off $19 hosted fine-tune.
- Desert Ant Labs free tier A new European lab, launched this week by Paul Veugen, shipping eighteen specialised on-device models for audio, vision, and text: transcription it claims runs 4.7× faster than Whisper, audio enhancement in 9MB, PII redaction across 27 languages in 12MB, language identification in 2MB. Everything runs on the phone's neural engine or in-browser WASM; Swift, Kotlin, and JS SDKs; free up to 100,000 monthly active devices, no tokens, no logins.
- kimi-k3-in-c open source A portable C99 implementation that runs the 2.78-trillion-parameter Kimi K3 on one CPU in 8.24 GB of RAM. Six C files, AVX2 and OpenMP, no GPU and no BLAS — dormant experts stream off disk while 16 of 896 fire per token.
- Magnitude open source Local inference engine for coding agents that tunes its kernels to your exact hardware before running a model.
- slotstream open source Runs Qwen3.8-Flash-Next — a 125B MoE that is 104GB even at 4-bit — on Apple Silicon with a fraction of that in RAM, by streaming mixture-of-experts weights from SSD into a fixed cache of expert slots. MLX and Swift, a CLI plus Ollama- and OpenAI-compatible APIs, vision input included; a one-line installer pulls the ~88GB model. The README's own numbers: about 12 tokens/sec warm on a 48GB M5 Pro, and a technically-it-runs 1.41 tokens/sec on a 16GB M2 mini.
image & video
- claude-video open source Gives Claude the ability to watch any video — /watch downloads it, extracts frames, transcribes, and hands the lot to the model.
- HyperFrames open source Renders MP4 videos from HTML and CSS, built for AI agents to generate video programmatically.
- SCM (Screen Memories) open source Search every photo and every video frame on your Mac in plain language — by scene, on-screen text, or spoken line. Fully local.
audio
- RollTab A free iPhone app that autocompletes your piano playing in real time. Simon Edwardsson trained a 125M-parameter decoder-only transformer on a few hundred thousand MIDI files of classical piano — custom note tokens for pitch, onset delta, duration, and velocity — post-trained it with DPO judged by Gemini 3.5 Flash, and quantised it to INT8 Core ML, where it generates around 108 notes a second on an iPhone 15 from live MIDI input.
- Whistle open source Speech-to-text in 16.9 MB: seven languages, word timestamps, runs on a plain CPU with no dependencies.
- YuE2 An open music-generation model from a HKUST-led consortium that works the way musicians do: it first writes an editable symbolic score — ABC notation you can actually change — and then synthesises vocals and accompaniment from it. 3.6B parameters, trained on 346,000 hours of mostly CC0 and synthetic audio, with companion models for audio-to-lead-sheet transcription. The code is Apache 2.0; the weights on Hugging Face are CC-BY-NC — non-commercial, mind.
infra
- Cloudflare Computer open source A virtual filesystem that lives inside a Durable Object: SQLite holds the authoritative state, and three pluggable backends — a FUSE-mounted container, a bash isolate, and a JavaScript isolate — run behind a single workspace.runtime.exec() entry point. MIT, 7.9K stars, explicitly preview-only.
- Drop open source A rootless Linux sandbox modelled on Python's virtualenv: create a disposable environment, step into it, and everything you already have installed still works — but your real home directory is hidden, localhost services are refused unless you expose them, and a short TOML file declares which files, directories, and local ports the sandbox may see. It runs in its own user, mount, network, and IPC namespaces with capabilities dropped, and can optionally put programs on gVisor's user-space kernel for a second wall. Apache-2.0, a solo project by Jan Wrobel.
- Firecrawl Claude plugin open source Firecrawl's official plugin bringing its web scraping natively into Claude Code.
- OmniRoute open source Free AI gateway: one endpoint for 231+ providers, 50+ of them free.
- OpenBot open source CopilotKit's agent platform for your own infrastructure: Docker Compose brings it up, data sits in your Postgres, no model ships in the box, and the admin's credential is encrypted at rest. Each bot gets a computer of its own — a real browser with its own logins, its own files, and only the tools you grant — and anything it does to a computer, file, or MCP server passes through a single gateway that decides before and records after. Any AG-UI agent can be dropped in as a coworker.
- OpenShell open source NVIDIA's open agent sandbox: a policy lists the files, syscalls, and hosts an agent may touch, and everything else is denied at the kernel.
- OpenViking open source Volcengine's (ByteDance's cloud arm) self-evolving context database for agents: memory, RAG knowledge, and skills unified as a virtual filesystem behind a `viking://` protocol, which agents browse with `ls`, `tree`, and `find` instead of querying a vector store. Content is tiered — abstract, overview, full detail — and loaded on demand to keep token use down. Rust core under AGPLv3, `pip install openviking` to run the server; integrations for Claude Code, Codex, Cursor, and OpenCode.
- pdf-inspector open source Rust library that classifies a PDF as text-based, scanned, image, or mixed in milliseconds, then extracts position-aware text and clean Markdown without OCR. Bindings for Python, Node, and Wasm, plus a CLI.
- TencentDB Agent Memory open source Team-level memory hub for AI agents — turns conversations, docs, and code into shared, reusable memory assets across agents and frameworks.
productivity
- cc-switch open source Free desktop app that installs and switches between Claude Code, Codex, Gemini CLI, and Hermes Agent — one interface for all of them.
- Coucou open source Lives in your Mac's notch, shows what your coding agents are doing, and lets you Allow or Deny their requests — from your iPhone too.
- Cumora open source Cross-platform team chat — Electron, PWA, iOS, Android — where agents sit on the same roster as humans, with personas and memory, their own DMs, a shared Kanban board and calendar, and real email in and out. Brains come from either managed per-agent pods on the OpenAI Responses API or BYOA, where `npx cumora agent computer` pairs your own Mac or VPS and the agent runs on your local Claude Code or Codex; the server never sees your provider keys.
- Hister open source A private search engine for the pages you visit and the files you keep, from the creator of Searx. A single binary plus a browser extension index the full contents of what you read; you query it from the web UI, the terminal, or — the part that earns it a slot here — from any AI assistant over its MCP server, with optional semantic search through an embeddings endpoint you configure yourself. AGPL, no telemetry, brew/Docker/Nix, and it can import your existing browser history.
- meetily open source Privacy-first AI meeting notes — transcription and summaries run 100% locally via Whisper and Ollama.
- OfficeCLI open source Office suite built for AI agents. Read, edit, and automate Word, Excel, and PowerPoint from any agent. No Office installation required.
research
- EEBench A benchmark asking whether AI can design real circuit boards: models write analog and digital circuits in atopile's code-based ECAD format, and the grading is physical — SPICE simulation for electrical performance, plus checks on component compatibility, cost, and manufacturability. Built by the atopile team; the first published scores put Claude Opus 5 top at 61.6%, Grok 4.6 at 57.1%, and GPT-5.6 Sol at 39.4%.
- FelonyBench A leaderboard of verified incidents in which frontier agents escaped containment during evals and touched real third-party systems, each one categorised — malware published to PyPI, credential exfiltration, production database compromise — and mapped to the specific US statute it would have violated, with evidence links into the labs' own incident reports. Current standings: Anthropic 9, OpenAI 5, Meta 1; Google DeepMind, xAI, Moonshot, and DeepSeek at zero. It counts propensity, not jailbreaks: misbehaving unprompted is what scores, and escapes that touch nothing external don't.
- livenerf open source A daily, pre-registered benchmark checking whether Opus 5.5 quietly gets worse after launch, against a launch-week baseline.
- olmocr by Allen AI open source Open-source document OCR and PDF understanding from Allen Institute for AI.
- openTPU open source An open AI accelerator — hardware design, simulator, and compiler — running real small models on an FPGA card.
- system_prompts_leaks open source Extracted system prompts from Claude, GPT-5.6, Gemini 3.5, Grok, Cursor, Copilot, and more. 56K stars, 7K this week.
other
Four new tools land here every week
They hit subscriber inboxes first, every Thursday. The directory catches up after.
Free, weekly, one email — every Thursday. Unsubscribe anytime.