#ai-agents

Organize your intent, loop your work and achieve the outcome you want from AI without wasting tokens

a11y-computer-use: accessibility-first computer use for AI agents. Pruned a11y-tree snapshots, element refs instead of pixel coordinates, a safety layer, an MCP server and CLI. macOS, Windows, Linux, and Chromium over CDP.

Python SDK for astrology, Vedic kundli, BaZi four pillars, feng shui, tarot, numerology, horoscope, I Ching, biorhythm and more. One multi domain API key, sync and async. AI agent and MCP ready.

Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.

Layered, replicated, self-adjudicating code review orchestrator

The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for calling more than 200+ LLMs.

Pre-install security for AI agents, npm packages, and MCP servers. Zero-dep local static analysis; normal scans never execute package code.

Python SDK for Agent Passport System identity, scoped delegation and signed receipts.

The open-source agentic framework to build, orchestrate, and operate production AI agents.

Reboot-proof terminal multiplexer for AI-native devs — a tmux alternative that persists your whole workspace across reboots and auto-resumes Claude Code & OpenCode sessions. Ships an MCP server so AI agents can drive your panes. Go, cross-platform (Linux/macOS/Windows). Apache-2.0.

Zero-trust governance layer for Claude Code. Policy-enforced MCP gateway with autonomy controls, middleware chain, audit log, HALT kill-switch, and prompt-injection defense.

A general-purpose semantic systems programming language. Describe a system once; real compilers lower the same source into engine builds, backend services, robots, web runtimes, and headset apps. Not a scripting language.

Self-hosted mission control for real Claude Code and Codex sessions — persistent terminals, automations, and browser/mobile control.

searchable local timeline for your AI agent work sessions

The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

occlusion for agent CLIs and APIs. Declare what an agent may run, and everything you did not name stays unreachable.

Context.dev Go SDK: scrape any URL to LLM-ready markdown, crawl sites, search the web and extract structured JSON with one API key.

A tmux-native workspace for multi-agent AI development across Claude Code, Codex, and Antigravity.

Python SDK and Rust broker for Adobe desktop automation through UXP and CEP bridges, connecting AI agent tools and DCC-MCP adapters to Photoshop, Illustrator, InDesign, Premiere Pro, and After Effects.

3ds Max adapter for the DCC Model Context Protocol ecosystem

`epsiloneridani` keeps the EpsilonEridani Lean library moving, using a "bring your own agent" approach

Give any MCP-capable agent persistent memory: remember/recall over a tiered store with hybrid vector + keyword retrieval. Single Go binary, SQLite or Postgres, embedded admin UI.

The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release) over a catalogue of curated packs: skills, subagents, and hooks, each installed in one line. It's npm for your coding agent. Any agent, any stack — Claude Code, Codex, Cursor, Copilot, Gemini, Kiro.

A Laravel security boundary for AI-triggered application actions. It bounds what an agent may do — authority, duplication, rate, approval — not what it was trying to do.

AI code sessions over your git repos run Claude Code / Codex / Cursor remotely, stream progress live, inspect diffs, open PRs, automate PR reviews. Go + React, ships as server or GitHub Action.

Deterministic HTML/CSS to PDF for Python, Rust, Node.js, C# and browsers. MIT licensed. Reports, invoices, previews and compiled variable-data documents.

a fast, rootless sandbox and virtual resource runtime. Run any workload in a real container, including an agent's tool-call or LLM-generated code.

The AI team that never forgets — persistent Memory Bank, 45 specialist agents, and 109 commands that survive every session reset. Install once via npx @hanzlaa/rcode. Works with Claude Code and compatible AI harnesses.

The AI-native application framework for Python — reactive UIs, APIs, agents, workers, realtime, MCP, and durable execution in one runtime.

Agent-first CLI for Proton Mail. Local AI inbox classification, search, and Q&A via Proton Mail Bridge and Ollama. Nothing leaves your machine.