ai-agents — independent software & tools
-
comandos
Mission control for running many Claude Code agents in parallel — live dashboard, actionable popups with full markdown, voice alerts, tabbed terminals, one-key answers, Telegram remote control. Linux, no cloud, survives reboots.
-
boardstate
Your dashboard is data. Any AI can build it; any human can edit it. A protocol + runtime for agent-composable dashboards — layout-as-data, one guarded control plane, sandboxed agent-authored widgets, MCP server included.
-
5dive
Run a company of AI agents on a server you own. Spin up named agents (claude, codex, grok…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a human must decide. MIT.
-
codevisor
The fastest native app for agentic engineering.
-
hypertaks-agent
Hypertaks = "A founder who owns a library of more than 1,400 books, knows exactly which book to consult for this issue, and has a strict SOP: intake → formulation → implementation → integration → documentation."
-
awesome-pi-agent-practices
Bilingual, evidence-led, reproducible practices for the Pi coding agent
-
visual-studio-harness
Agent Harness
-
multi-model-dev-sync
Run AI Coding Agents Side by Side 2026 - Multi-Model Dev Tool for Parallel Code
-
laya
Laya is an open-source, local-first AI notification command center that aggregates Slack, Gmail, GitHub, Jira, Notion, Outlook, Calendar (and more) notifications using local LLMs via Ollama and LM Studio. Supports cloud models via BYOK.
-
veilbrowser
Stealth browser for AI agents — real Chrome over raw CDP, no Playwright/Puppeteer. TypeScript + MCP-native. Passes sannysoft 57/57, bypasses Cloudflare.
-
agent-handoff-kit
為 Agentic AI 新手友好的輕量項目記憶與治理套件：把狀態、決策、下一步、文件地圖、新手引導與工具邊界寫成標準檔案，讓不同 AI 工具可在同一項目資料夾內跨 Session 對話延續工作。 A beginner-friendly project memory and governance kit for Agentic AI, helping AI tools continue work across chat sessions with standard project files.
-
openmarket-ai
OpenMarket.ai — Agent-to-agent marketplace on Hedera. AI agents buy and sell services. Auto-payments via HBAR. MCP, SDK, LangChain, CrewAI.
-
CodeyBox
Runs CLI coding agents (Claude Code, Codex, Copilot, Cursor, Gemini, opencode) against a task queue. Each works in an isolated VM; output is checked by configurable auditors, then merged via git. Pools multiple provider subscriptions with quota-aware routing and fallback. C#/.NET 10, MIT-licensed.
-
claude-skills
Open-source Claude Code skills that bring planning, building, and verification gates to agentic coding workflows.
-
OpenBcon
Open-source AI funding workspace for consultants, advisors, and incubators. Manage opportunities, companies, applications, and AI-generated funding packages.
-
OpenBcon
Open-source AI funding workspace for consultants, advisors, and incubators. Manage opportunities, companies, applications, and AI-generated funding packages.
-
knowledge-os-plugin
Portable, OKF-compatible company knowledge base in Markdown. Compiles to a hierarchical, scale-ready index for LLMs + an offline HTML viewer for humans — with facets, search-by-meaning, and built-in agent procedures (onboarding, dedup, capture). Works with Claude Code, Codex, Antigravity — or no agent.
-
OWNEX
OWNEX — Autonomous Work Operating System: opportunity discovery, security automation, agent orchestration, local-first AI routing, revenue intelligence. Python/FastAPI + Vue 3 + Tauri.
-
beyond-ai-collaboration
Document-driven AI engineering collaboration for Codex: govern goals and permissions, execute design-to-ops tasks, prove results, and grow project knowledge.
-
forge
Fast, model-agnostic AI coding harness and CLI in Rust — routes every task to the optimal model for cost × capability.
-
agent-engineering-toolkit
Proof-carrying workflows for coding agents: bind tests to exact code, detect stale evidence, review scope, and hand proof across agents.
-
agentforge-runtime
AgentForge Protocol + Cloud: create, run, monetize, evaluate, and operate AI agents across APIs, marketplaces, workflows, channels, and enterprise operations.
-
ctxone
Persistent, searchable, accountable memory for AI agents — the shared team memory layer. Eliminate context anxiety.
-
shelf
Local tool library for macOS — keep the tools you build, launch them in a click, and share them honestly with your AI agents over MCP. Local-first, no account, MIT.
-
clauderabbit
ClaudeRabbit is a free, open-source security product protecting the open-source community from malware. We clone any public GitHub repo into an isolated sandbox, run it, and return one honest safety score.
-
aileron
Tamper-evident flight recorder for AI agents - hash-chained, signed audit log of every tool call, with MCP proxy policy enforcement and anomaly detection.
-
aipermission
Local-first permission gateway for AI agents: connector-based SSH, Postgres, and Redis access with scoped tokens, human approval, audit logs, and encrypted local credentials.
-
apogee
Local-first terminal coding agent for any OpenAI-compatible endpoint — local or cloud. Full agentic tool loop, OS-enforced sandboxing (Landlock / seatbelt / Windows token), sessions, MCP, and A/B-measured mechanisms that make even small LLMs (4B–35B) deliver. Go + Bubble Tea.
-
ralph-wiggum-codex-review-triage
Codex Autonomous Objective Loops 2026: AI with Mandatory Review & Verification
-
roadkeep
Keeps a project's roadmap, changelog, improvements and strategy files to one format - a schema at the point of insertion, not a linter after the fact. Python CLI + Claude Code plugin.
-
renforge-mcp
Free, open-source MCP server for Ren'Py visual-novel development — give AI agents full control of a Ren'Py project (analyze, write, run, see, test).
-
first-run
Embeddable customer-activation agent for small B2B SaaS companies
-
huqan
Local-first, deterministic verification layer for AI claims, memory writes, and risky actions.
-
darkflow
AI workflow installer: 5-layer docs structure + GitHub Issues triage loop for Claude Code projects
-
repomon
Run a fleet of AI coding agents (Claude Code, Codex, Aider) across many repos — Rust TUI, tmux-backed.
-
claude-code-from-scratch
Build Claude Code from scratch with a step-by-step tutorial in TypeScript and Python for learning agent coding tools
-
AladdinAI
AladdinAI: open-source BYOI (Bring Your Own Infrastructure) AI Agent platform. Connect your own VMs, NVIDIA NIM, OpenAI, Anthropic, Ollama — build and manage AI agents visually.
-
readme2demo
Verified tutorials and demo videos from your README. An AI agent runs it in a hardened Docker sandbox and replays it in a fresh container before anything is published.
-
altai-app
Local-first, open-source desktop workspace for AI coding agents.
-
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.
-
agentweb
Turn websites into fast CLI commands that any coding agent can use
-
agent-forge-cli
Memex.ai-Inspired AI Knowledge Base 2026 - Smart Markdown Wiki with Graph Search & Static Publishing
-
edgeverdict
A code review gate that verifies changes by executing tests, not by judging diffs. LLM proposes; a deterministic gate decides.
-
fak
fak — the Fused Agent Kernel: one Go binary for AI agent loops. Wrap Claude Code/Codex/Cursor, keep long sessions cache-efficient, route work per call, run local GGUF models, and adjudicate tool calls.
-
olympus
Self-hosted, partitioned agent-memory fleet: bare-metal Debian setup + mem0/Qdrant/Ollama stack + Hermes/Claude Code/OpenCode/Pi integrations, run from one olympus CLI/TUI.
-
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.
-
dotagents
My main list of vendor-agnostic agent skills and harness configs
-
ragleap-core
The open-source core of RagLeap — a self-hosted RAG chat engine (document ingestion, retrieval, citations) powering RagLeap's full AI business manager: Voice AI, WhatsApp/Telegram/Discord bots, database & CRM integrations, workflow automation, and a private executive assistant. Foundation layer — hosted platform at ragleap.com
-
argus-agent
A harness that makes a small (or modest) LLM reliably run multi-step agentic tasks — tools, skills, memory, scheduling.
-
shipwright
The open-source autonomous delivery agent for Claude Code.
-
automaton
AI coding agent framework — portable, stage-gated harness for Claude Code, Codex, and OpenCode
-
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.
-
ai-badger
Source-of-truth marketplace + project scaffolder for custom Claude/agent skills, personas, and instructions. Organized as {stack|common}/{feature}; welcome-ai-badger scaffolds a repo, feed-badger contributes back.
-
ai-raccoon
Give AI agents a memory that outlives the session: local-first SQLite per project, hybrid search, workspace sandboxes, and optional cloud sync.
-
flutter-skills
Production-ready AI agent skills for Flutter and Dart development—architecture, performance, security, platform integrations, and releases.
-
partyline
One wire, every agent — a shared telephone line for Claude Code agents. (It's a JSONL file.)
-
twin-brain
A second brain that builds itself: Claude Code maintains a persistent, interlinked Markdown wiki you own, with a local web app, Apple Calendar/Reminders integration, and token-budgeted automation. No database, no API keys.
-
exomem
Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.
-
FixMap
Local-first repo maps for coding agents—ranked files, test routes, risks, CLI/MCP/GitHub Action, and public GitHub URLs.