ai-agents — independent software & tools
-
spec-flow-framework
Nam-Cheol/namba-ai → AI Work Manager: Turn Vague Ideas into PR-Ready Specs & Evidence 2026
-
0n1x
0n1x — Proof of Agent Execution. The neutral, signed trust layer for AI agents: verify before you pay, signed facts not judgments. The Carfax for AI agents.
-
onyx-mcp
Proof of Agent Execution — the neutral trust layer issuing portable, signed execution credentials for AI agents (x402 · MCP · ERC-8004).
-
soma
Batteries-included RMCP runtime and scaffold for shipping Rust MCP servers with CLI/REST/HTTP MCP, auth, providers, plugins, and generated contracts.
-
LinkMap
A modern Internet Library and curated directory of websites to discover AI tools, movie streaming, live TV, anime, games, developer resources, learning platforms, and thousands of useful websites.
-
eyes28-store
EYES28 - give any AI model eyes. Videos, web pages, pictures and voice, rendered locally in ~1.1s per page. No API keys, no telemetry. Windows, macOS, Linux.
-
second-brain-setup
Personal knowledge management system for Claude Code. Obsidian vault as external memory that grows with every session. 5 slash commands, AI-First notes, Obsidian graph. Based on Karpathy's LLM Knowledge Bases.
-
scala-semantic-harness
Semantic tooling for Scala coding agents, combining compiler/test truth, SemanticDB, presentation-compiler evidence, symbol reconciliation, FP analysis, and an agent-friendly CLI/MCP interface.
-
claude-session-tint
Know which Claude Code session needs you. Tints your terminal window by project and lights it up when a response lands unseen. MIT.
-
rekon
A codebase intelligence substrate for architecture-aware agents, repository governance, and explainable software context.
-
code-meridian
Local graph memory for AI coding agents, giving MCP-compatible tools precise codebase context before they edit.
-
artificer
Artificer — the hive that forges software. Self-hosted autonomous AI dev team: crew board breaks goals into tickets, local models build them, verify gates (tests + golden-frame + visual diff) prove done. Local-first via Ollama.
-
caprock
Mission control for Claude Code — run, observe, and orchestrate your agent sessions locally. Live activity, cost & token burn, loop detection, verified multi-agent tasks.
-
claude-code-memory-setup
Reduce token usage and add long-term memory to Claude Code using Obsidian and Graphify for efficient codebase awareness.
-
work-harness
A multi-agent delivery harness for Claude Code: decompose a backlog into PR-sized units, dispatch one autonomous lead per unit across local/SSH/cloud hosts, and drive every PR to merged through a persistent shepherd.
-
AI-Atomic-Framework
The safety brake for naked AI coding. A deterministic governance layer that lets N coding agents concurrently mutate one repo — via 5D CID identity, a 7-stage lifecycle, SHA256-anchored closure evidence, and atom maps that retire legacy modules through a gated replacement lifecycle.
-
octo-code-trail
Rustic SQLite Code Graph 2026 – 28 Languages, 238 Commands, Zero API Keys
-
enclave
Sandbox for running AI coding agents autonomously: isolated, network-restricted, host-safe
-
marketnow
Trust layer for agent commerce. 8,560 MCP skills, Sentinel L1.5 security audits, AP2 mandates, x402 payments. Open source MIT.
-
skill-flare-discover
Best AI Agent Skill Finder 2026 – Multi-Registry Install & Security Labels
-
vibe-council
A local multi-model council for developer workflows: review plans, critique diffs, extract decisions, and keep project-local AI decision memory.
-
mozg
Exam-scored knowledge brains for AI agents: paste a docs URL, get a searchable brain over MCP with a measured score and known gaps. AGPL.
-
news-briefing
Auditable daily news briefing with a code-enforced source window, model-ranked stories, and structural corpus checks.
-
loadout
Equip the right context for the job — named context kits for AI coding agents, auto-equipped per stack, machine, or task
-
ticket-master
Cross-platform multi-provider LLM ticket router & AI coding agent triage console. Files structured tickets, scores, and routes to Claude Code, Codex, and Gemini.
-
owledge
Markdown-first persistent memory and project planning for AI agents, existing knowledgebases, and multi-agent workflows.
-
argus
Deterministic supervisor for multi-agent AI coding workflows: spawns workers, verifies diffs against git (not self-reports), and ships PRs. Written in Go.
-
empir3-bridge
Local-first MCP bridge — orchestrate the AI CLIs you already pay for (Claude, Codex, Gemini, Grok) and drive a real browser + desktop, all from one agent.
-
AIsland
A local-first multi-agent status island for Windows
-
engsys
An AI engineering team you install into any Claude Code project — stack-agnostic agents plus a deterministic installer. Swap stack packs, not prompts.
-
better-codex
A task board and Agent system inside Codex Desktop. Local-first, open source, macOS and Windows.
-
deepseek-plugin-store
DeepSeek Harness 独立社区插件商店：发现、安装并提交经过验证的插件、工具与扩展。 | Independent community plugin directory.
-
agentpantry
Your agent machine needs your logins. Pantry ships them sealed. Opt-in AES-256-GCM browser session and secret sync for AI agent hosts.
-
relay
Native macOS terminal for running many coding agents in parallel. Swift 6 + AppKit, SwiftTerm engine, agent state from Claude Code hooks instead of output parsing. Workspaces, split panes, triage dashboard. ~90 MB resident, 2.4us added input latency. brew install --cask essedev/relay/relay
-
fleet
Fleet manager for Claude Code: one manager session spawns, steers, and monitors many durable headless Claude Code agent sessions in parallel across projects. Mid-turn steering, token budgets, usage-limit park/resume, journals + respawn, git-tracked knowledge loop. Single-file stdlib-only Python CLI. No daemon, no deps.
-
DeepLaw
DeepLaw 2.0：本地优先单用户 Agent Knowledge OS，融合自主长期记忆、Markdown-native 知识、可信 Ledger、有界上下文与可验证法律证据。
-
hologram-builder
Build and manipulate 3D objects in real-time using gesture-based hand tracking and AI. Cross-platform desktop application powered by Electron and Three.js.
-
AWSBestPracticesSkill
Unofficial source-linked AWS best practices for every AWS service, organized by Well-Architected pillar for Claude Code, OpenAI Codex, and AI coding agents.
-
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.
-
cartopian
Turns any AI into a Project Manager with planning and governance
-
superseo-skills
Automate SEO audits, briefs, and content strategy using eleven production-tested Claude skills that perform independent research without external data input.
-
signal
A political intelligence pipeline
-
flight
A graphics and application SDK for AI agents.
-
fgentic
Sovereign AI-agent collaboration platform: humans and agents in Matrix rooms, A2A delegation, open standards, Kubernetes-native GitOps.
-
openclaw-n8n-stack
Deploy an OpenClaw and n8n Docker stack for AI agents, MCP, and workflow automation in one setup
-
mwe-mcp
Persistent, structured memory for AI agents — a human-readable Markdown wiki, multi-user with per-fragment ACL, self-organizing overnight. Agent-agnostic via MCP. Self-hosted, AGPL.
-
pakemin
An AI Engineering Specification for vendor-agnostic project knowledge.
-
DalamudAgentBridge
Authenticated local bridge and MCP tooling for safe agent-assisted Dalamud plugin development.
-
better-md-skill
Markdown documentation engineering skill for AI coding agents. Improves, restructures, audits, and validates READMEs, API docs, tutorials, and changelogs with CommonMark and GFM awareness, a validation gate, and a 51-case anti-fabrication test suite.
-
aspicio
DXF and vector-PDF viewer for the web and AI agents — TypeScript parse→tessellate→render engine with a WebGL viewer, React/Vue/Svelte/web-component bindings, HTTP API, MCP server, and an in-chat viewer for ChatGPT & Claude (MCP Apps)
-
agent-claim-network
面向终端的通用 AI 助手，让 Agent 之间共享可检索、可追溯且允许分歧的知识。让下一次判断，带着来源出发。
-
mem
A portable, self-hosted memory plane for AI agents — one core across API, MCP, CLI, and UI.
-
Clawness
A Claude Code plugin that injects the right coding, security and scientific-computing rules into every prompt. 195 rules across 28 domains, including test-quality rules derived from mutation-testing its own suite. Plus a plan-approval gate, access guard, per-project memory, session handoffs and red/blue-team review agents.
-
pluidr
Opinionated engineering workflow installer for OpenCode, Plan, Build, Review, Debug.
-
spectre-graph
Spectre AI 2026: Next-Gen OSINT Engine & Autonomous Graph Disambiguation Toolkit
-
SheshAOS
Governance-first, event-sourced AI operating environment for Ubuntu Linux — Rust workspace, 12 crates, 981 tests, provider-agnostic LLM streaming.
-
gecko-surf
The knowledge graph for APIs your agent can trust. Maps any API — even messy, paywalled, or on-chain ones — into a verified graph your agent traverses instead of guessing, and simulates any action to a receipt before money moves.
-
geml
One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.
-
nexus-project-client
Nexus Projects — source-available Application for AI-coordinated project & task management (text + voice Coordinator, plans, tasks, agents).
-
agentflare
Run AI coding agents efficiently, and coordinate more than one of them. Zero fluff, zero runtime deps.