ai-agents — independent software & tools
-
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.
-
veilbrowser
Stealth browser for AI agents — real Chrome over raw CDP, no Playwright/Puppeteer. TypeScript + MCP-native. Passes sannysoft 57/57, bypasses Cloudflare.
-
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.
-
forge
Fast, model-agnostic AI coding harness and CLI in Rust — routes every task to the optimal model for cost × capability.
-
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.
-
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.
-
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
-
automaton
AI coding agent framework — portable, stage-gated harness for Claude Code, Codex, and OpenCode
-
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.
-
akashic-aurora
Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.
-
VecMem
Manage LLM agent memory with a resource-aware dual-tier system that uses HNSW indexing to balance short-term context and long-term knowledge retention.
-
agent-orch
Run local coding agents in a cross-audit loop on any git repo — author, cross-audit, test-gate, merge
-
bike4mind
The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.
-
chimera-agent
Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully yours.
-
gnosis
Gnosis is a Greek noun meaning "knowledge" or "awareness"
-
KarvyLoop
The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents on your machine.
-
wavemind
Local-first dynamic memory for agents and apps: SQLite source of truth, vector search candidates, hotness, decay, TTL, namespaces, and benchmarks.
-
my-opencode
OpenCode configuration with agents, skills, review guardrails, and a GitHub Issues workflow bundle.
-
tess
One CLI for your whole machine: code worktrees, notes/brain, offline local AI, and Mac messages/calls/calendar — for you and your AI agents.
-
director
Coordination ledger for coding agents: what was decided, what's still open, where you parked — durable across sessions, repos, and weeks. Memory tools store what the agent knows; Director tracks the state of the work. Run both: they don't overlap. Claude Code + OpenAI Codex.
-
free-ai-tools
Build AI applications with this curated collection of free LLM APIs, coding copilots, and infrastructure tools.
-
awesome-ai-native-os
An atlas of AI-native production systems and domain operating layers
-
factory
Open-source compiler for AI agents. Write one crewhaus.yaml; compile it to a CLI, a Slack bot, and an eval harness from the same spec. Apache-2.0.
-
CODY
CODY AI >> brought to you by CRYSNOVA_AI
-
cyborg
Open-source collaborative AI agent platform. Humans and AI agents on different machines work together in shared workspaces — agents run locally on your own daemon, self-hosted, no cloud execution of your code.
-
sportsdata-agents
Free, open-source agentic sports-data workbench — an agent team over live odds + stats: arbitrage & value detection, backtesting with CLV, monitors, racing, fantasy. BYO model key.
-
bigpowers
72 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers
-
peacock
Stateless Rust renderer and MCP-App host for agent-authored, agent-consumed data reports — turns an escurel report skill into an A2UI + Vega-Lite artifact for MCP hosts, chat, and agents, with view state synced to the conversation.
-
atomic-agents-stack
AI agents that live in your folder, not someone else's database. Vault-native, MIT-licensed. 21 spec docs + Python reference implementation.
-
onyx-mcp
Proof of Agent Execution — the neutral trust layer issuing portable, signed execution credentials for AI agents (x402 · MCP · ERC-8004).
-
claude-code-memory-setup
Reduce token usage and add long-term memory to Claude Code using Obsidian and Graphify for efficient codebase awareness.
-
marketnow
Trust layer for agent commerce. 8,560 MCP skills, Sentinel L1.5 security audits, AP2 mandates, x402 payments. Open source MIT.
-
instincts
Working-instinct skills for Claude Code: verify claims against the source, log for the bug you can't reproduce, write like a human, test so the test bites. A reflex layer on top of superpowers.
-
flight
A graphics and application SDK for AI agents.
-
glyph
Glyph is a workbench for composing the forms intelligence takes today — and discovering the language it will speak tomorrow.
-
DeepSeek_Science
Rust-first Science Agent Kernel for reproducible, auditable, cache-aware STEM workflows.
-
ai-engineering-production
AI Engineering Roadmap 2026 🚀 | Build & Deploy AI Apps from Scratch
-
Qyvaria
Qyvaria OS and Qyvaria AI Software: an open-source AI engineering platform with qyvaria.py kernel corpus, local AI workflows, agents, monitoring, prompt generation, QyChat, AI BIOS, and hard-logic automation.
-
hopbox
A compute-box substrate: one daemon turns a host into a fleet of isolated Firecracker microVMs reached over plain SSH — for humans and AIs. Your SSH key is your identity; the username is the box spec.
-
potion
🧪 The magic potion for Claude Code — a lean project framework: plans are prompts, disk is memory, evidence or it didn't happen. Brewed itself to v1.0.0.
-
cys-terminal
AI agent fleet orchestration terminal — bidirectional socket IPC, resource governance, mission-control dashboard. macOS · Windows. Built largely by AI agents under human direction.
-
polygate
An MCP server that lets any LLM research and trade Polymarket. Point Claude, Cursor, or VS Code at it and your agent can read markets, prices, and your account — and place real trades. Optional REST gateway for algorithmic bots.
-
tankpkg-skill-vault
Secure AI Agent Skill Manager 2026 – Tamper-Proof Package Engine for Tank
-
box
Box — self-hosted Claude Code in your pocket. Run real Claude Code & Codex sessions on your own server, driven from your phone (native chat UI, voice, files, skills, always-on).
-
hyperspace-terminal
Hyper Terminal 2026: Next-Gen Web Tech CLI ⚡ | Free & Open Source
-
context-kit
4 PCA templates + 5 Claude Code skills — give any AI agent deep personal context. One-command install.
-
autodrive
Autonomous engineering pipeline for Claude Code — /drive runs the task lifecycle (plan → implement → review → harden → finalize → ship) with two human gates, gstack planning, and codex cross-model review.
-
open-cowork
Open Cowork is a desktop, cloud and gateway workspace for OpenCode.
-
aarg
Local-first Rust CLI that tailors your resume to a job posting through an adversarial agent loop, and never invents experience you don't have.
-
codex-safe-starter
Safe repo-local starter template for Codex guidance, skills, read-only agents, conservative config, and no-key validation.
-
koino-insurance-os
RepFlow — insurance agency OS for life & health distribution. Static React + Supabase. Deploys to repflow.koino.capital.
-
Sparra
Adversarial build harness with cross-model judging (Claude builds, Codex judges) and a holdout wall. Drive it from Claude Code or run it unattended.
-
memroos
MemroOS / memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.
-
awesome-persona-skills
Distill human behaviors, roles, and personality traits into reusable AI agent skills for your projects.
-
forgeterm
Monitor AI coding agents in real-time to block unauthorized file access, network connections, and dangerous commands while enforcing system resource limits.
-
CrewLoop
A team of specialized AI agents covering the complete software development flow — from requirements discovery to deploy. One responsibility per agent, specs as source of truth, no shortcuts.
-
awesome-agent-skills
Curated, auto-updated awesome-list of vetted AI agent skills with quality ratings for Claude, GPT, a
-
mcp-servers-live
Auto-updated index of MCP servers shipping on GitHub, refreshed every 15 minutes
-
skills-tracker
Real-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend