developer-tools — independent software & tools
-
unbluff
Self-verification hooks + a reasoning skill for Claude Code - keep the agent honest across your prompts, its claims, your tests, parked work, and memory. Fail-silent, stdlib-only, no network.
-
terse-sharp
Roslyn-powered MCP server for .NET — your coding agent stops reading whole C# files. 13-30x fewer tokens: semantic navigation, compile-gated edits, solution-wide rename, and type-checked XAML bindings for WPF/Avalonia/WinUI/MAUI. No IDE, no licence, one install.
-
adversarial-gatekeeper
AI Content Guard 2026: Adversarial Fact-Check Gate for Error-Free Code & Copy
-
agentweb
Turn websites into fast CLI commands that any coding agent can use
-
agent-os
Open-source local-first task board and macOS control plane for OpenAI Codex, with MCP plugins, durable tasks, and multi-project workflows.
-
edgeverdict
A code review gate that verifies changes by executing tests, not by judging diffs. LLM proposes; a deterministic gate decides.
-
francois
Mission control for your Claude Code fleet — a native desktop app (Tauri 2 · Rust · React) to run and supervise multiple Claude Code sessions: live transcripts, diffs, subagents, MCP servers, and a real shell in one window.
-
runbookproof
Continuously verify commands in documentation, runbooks, and AI-generated instructions.
-
kotlin-lib-mcp
MCP server exposing the sources, public API and KDoc of Maven-published Kotlin/Java libraries
-
kotlin-lib-mcp
MCP server: gives your AI agent the real sources, public API and KDoc of any Maven/Gradle-published Kotlin or Java library
-
plandex
Plandex is an open-source, terminal-based AI coding agent designed to take on large, multi-step software development tasks across many files in real world codebases. Written in Go and released under the MIT license, Plandex builds and executes long-running "plans" — durable, branchable units of work that combine intelligent context management…
-
shipwright
The open-source autonomous delivery agent for Claude Code.
-
avatar-mix
Generate professional videos from scripts or URLs using HeyGen avatars, dynamic layouts, automated captions, and custom audio effects.
-
automaton
AI coding agent framework — portable, stage-gated harness for Claude Code, Codex, and OpenCode
-
niro
Security that keeps up with your developers.
-
nahuali
Self-inspecting, auditable memory for AI agents: it surfaces the evidence, provenance, and health behind each recall so callers can see which memory to trust. Optional Ed25519-signed tamper-evident ledger. Local-first, Rust.
-
flutter-skills
Production-ready AI agent skills for Flutter and Dart development—architecture, performance, security, platform integrations, and releases.
-
glossa
Make ChatGPT your local coding agent
-
claude-code-reverse-engineering
Explore reverse engineering specs for Claude Code CLI, with implementation-ready design docs from source map analysis of the npm package
-
AdGen
Point it at your repository, get a video ad. Free, GPL-3.0, no ads, no account — drives the AI subscription you already have and renders locally with ffmpeg.
-
FixMap
Local-first repo maps for coding agents—ranked files, test routes, risks, CLI/MCP/GitHub Action, and public GitHub URLs.
-
sbx
Per-branch sandboxes that sleep when nobody is using them. Your own databases per branch, task or agent - 191ms wake, 0 B idle, one static binary, docker or kubernetes.
-
Actionables
Local execution coordination for OpenAI Codex. Turn technical findings into scoped, evidence-backed tasks with MCP integration and validation.
-
ashlr-hub
Local-first command center for agentic engineers — the CLI + Raycast hub and front door to the Ashlr dev-tool ecosystem.
-
Hyprchan-Assistant-Preview
Hyprchan 2026: Anime AI Assistant for Linux & Hyprland 🎌 | Waitlist & Updates
-
scribe-describe-generate
🚀 Sago AI: Generate Any App from a Markdown Description in Seconds (2026)
-
assaio
Is your AI coding spend delivering? Offline-first analytics for Claude Code, Codex CLI, Gemini CLI, and Cline — $/100 AI lines per project, honest diagnostics, a self-contained dashboard, exec plugins in any language, and a self-hosted team server. No telemetry; prompts are never read.
-
workhub
Tauri 2 all-in-one developer hub: task board backed by an Obsidian vault and Claude Code plugin marketplace
-
unbraid
Unbraid a tangled working tree into atomic commits, with AI-written messages.
-
queryforge
Let your users ask your database anything, in their own words — safely. The model fills in a validated Query AST, never a query string, and deterministic Go compiles it to SQL, MongoDB or whatever backend you add. Config-driven, read-only by design, standard-library Go.
-
axon
A lightweight, AI-powered code editor built from scratch with Electron, React, TypeScript, and a Go backend. Features real file system access, multi-pane split editing, terminal, markdown preview, media preview, and a beautiful Sora dark theme with Catppuccin icons.
-
codex-coding-os
Spec-first workflow pack for OpenAI Codex: skills, AGENTS.md templates, workflow gates, fresh-context review, validation, and handoff.
-
gospect-mcp
Go-only, report-first code scanner exposed as an MCP server. Indexes a module, runs deterministic analyzers, and reports genuine bugs, dead code, stale docs & outdated APIs — never editing your code until you ask.
-
ai-commander-core
Kodiqa-agent 2026 - Open Source AI Coding Agent with 7 Providers & 69 Commands
-
signal-house
Signal House should make it obvious whether agent work is moving and where it is getting stuck.
-
agenticloop
Loop engineering for AI coding agents — shaping the whole run, not one prompt: a Markdown-first overlay of task records, role boundaries, verification evidence, and review gates that holds across multi-hour work
-
base-bash-libs
Sourceable Bash helper libraries for reliable shell scripts: error handling, logging, files, Git, strings, temp paths, cleanup hooks, and command runners.
-
Agent-Startup-Skills
Build SaaS products using an 8-phase AI agent pipeline with mandatory approval gates for Antigravity, Claude Code, and Codex.
-
terminal-win
BBARIT Terminal (빠릿터미널) for Windows — free AI vibe coding IDE, terminal & agent in one, built 100% in Rust. Ships ⚡ BBARIT Agent (built-in coding agent with a verify loop) + a 🦌 dev↔review AI pair, runs Claude, Codex, Gemini, Kimi, Qwen & Ollama side by side, and edits Word/Excel/PowerPoint. Free.
-
PastePilot
A lightweight macOS clipboard manager built for developers. PastePilot recognizes what you copied and suggests the next useful action — no plugins, no cloud, everything stays on your Mac.
-
rilable
Build iOS apps on your iPhone using AI agents that compile code in the cloud, manage sandboxes, and deploy directly to your device.
-
rails-senior-architect
Ultimate Rails CTO Toolkit 2026: Pro Opinionated Skills for Modern Apps
-
ExternalBrain
Self-improving, self-hosted memory across every AI coding tool, project, and team (Claude Code, Cursor, Copilot, any MCP client). Autoskill proposes new skills from your sessions, so each project improves automatically. Inspectable, grounded, and yours. Built for teams and enterprise. Open source, MIT.
-
open-prompt-library
The ultimate open-source prompt library. Over 2,100+ high-quality AI prompts structured into searchable markdown categories and raw exports.
-
keel
Keel turns coding agents into work owners: a project-neutral issue-to-done workflow backbone.
-
dsh-classic-coding
dsh·古法编程插件
-
dsh-tool-autoexpand
自动展开 DSH 界面中新增的工具调用结果卡片，带侧栏开关。标准 dsh 客户端插件
-
todox
Working memory for developers and their agents — an agent-first task log with decisions, dead ends and handoffs, reachable over MCP
-
daedalus
Daedalus is a standalone terminal-based AI coding assistant that runs on your machine. It connects to local LLM servers (LM Studio, Ollama, llama.cpp, vLLM) or remote providers (OpenAI, Groq, OpenRouter, Anthropic), routes requests intelligently, and gives your AI agent access to your file system, terminal, git, web search, and codebase indexing
-
tokn-dist
TOKN — download & try. A trust-first agentic coding/reasoning harness with 20+ regulated-domain plugs, offline licensing, and in-place self-update. Public binaries only (source is private). Start a 14-day trial: tokn license trial
-
weft
A VS Code-style desktop app for running many Claude Code CLI sessions as browser-style tabs, with live per-session status driven by Claude Code's own lifecycle hooks.
-
throng
A project-first terminal workspace — persistent, detachable terminals in a dockable layout, with a live file tree and code editor.
-
agentic-tui
Agentic orchestrator TUI: turns a goal into worktree-isolated claude -p sessions that plan, implement, and verify epics in parallel
-
mergemind
AI-powered GitHub issue finder that helps developers discover beginner-friendly open source issues, analyze repositories, and contribute faster with Google Gemini AI.
-
ada
From-zero terminal coding agent: a key-holding OpenAI-compatible routing backend + a thin client with ~285 skills, MCP connectors, and ask/plan/auto modes. No build step.
-
thegn
A terminal-native git-worktree IDE that is its own terminal multiplexer: one process, each repo a workspace, each git worktree a tab.
-
trusty-tools
Unified Rust workspace for the trusty-* AI developer-tooling ecosystem: hybrid code search, memory palace, code analysis, PR review, and the MPM multi-agent platform — MCP servers, daemons & CLIs.
-
trusty-tools
Unified Rust workspace for the trusty-* AI developer-tooling ecosystem: hybrid code search, memory palace, code analysis, PR review, and the MPM multi-agent platform — MCP servers, daemons & CLIs.
-
zeus
Local-first orchestrator for many Hermes Agent bots
-
vigia
A live diff monitor for the terminal pane beside your coding agent. Built to stay open, not opened once per review.