#agents

AI Agent Toolkit 2026: Smart Device Control for iOS & Android

Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub Copilot, and more) work as teammates in channels, threads, DMs, and shared tasks. Your data stays on your machines.

A programmable tool and agent runtime for Pi

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

Unofficial Google-Health-CLI for the Google Health API, written in Go

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done claims, patch sprawl, and tool loops in your Claude Code session.

A simple MacOS helper for safer exposure of secrets to your agents

Proxy server, which redirects requests to a custom API to Gaslight coding agens like Claudecode !!

Claude Code Skills, Agents & Plugins — UitKit

Deterministic authorization + tamper-evident audit for AI agents, humans, and workloads — one principal type, safety invariants machine-checked by an SMT solver (cvc5), every decision independently verifiable offline. Pure Rust.

The UI your coding agent should have implemented. Runs on localhost, designed for massively parallel work.

The package manager and compiler for AI agent skills — write once, run in Claude Code, Cursor, Codex, Copilot, Gemini CLI, and more

A gateway + skill letting Claude Code agents collaborate across machines

Async hierarchical memory middleware for LLM agents.

Keyless heuristic self-inspection tool: an agent describes a thought or task and always gets back one metathought. Deterministic routing over an open CSV (no LLM). REST + MCP.

Wolbarg — modular, provider-agnostic semantic memory SDK for AI agents

git diff for your agent's context window. See exactly what your LLM saw — turn by turn, block by block.

🚢 A crew of IDE agnostic sub-agents, slash-command workflows and tools that drive a GitHub issue from open to a reviewed, CI-green pull request — autonomously. Flagship: /ship-issue.

Permission-aware, evidence-grounded performance-review agent (ADK 2.0 + Gemini + Next.js) - Kaggle AI Agents Intensive capstone

Vinkius Open Data Initiative: The world's largest open-source database of Model Context Protocol (MCP) servers. Production-ready metadata connecting AI agents to APIs and enterprise tools.

Autonomy Composition Abstraction: a machine-readable charter format for defining authority, obligations, constraints, and escalation paths in multi-agent systems

Zero-infrastructure A2A messaging between AI agents on different machines — Claude, ChatGPT/Codex, Copilot, any harness; ntfy relay transport, no ports, no server

Long-term memory for AI agents that stays correct — zero-dependency Python + MCP server for Claude Code. When a fact is corrected, the old value stops coming back.

Trading agent that learns from his mistakes

Stop burning your Claude or Codex limits on boilerplate. Delegate multi-file implementation to Cursor's Composer 2.5 over MCP — your frontier model writes the brief and reviews the diff; Composer does the typing, fast, on a separate quota.

Personal markdown memory for coding agents — brain-modelled curator, three retrieval tiers, lives on your disk.

Reliability for LLM agents through enforcement, not model size — Agent-Contract-Kernel + a fail-closed orchestration engine. Model-agnostic. 🇦🇪 Built in the UAE.

CLI/MCP agent surface for Enji Guard

pi-fleet is Pi-native execution infrastructure for programmatic agent orchestration.

Voice AI agent that lets Romanians handle civic tasks by phone — pay taxes, file city reports, understand bureaucratic letters. One phone number, plain Romanian, any phone.

Master AI Skills Collection 2026 - Scalable Agent Scripts & Automation Hub

Local-first memory engine for AI-agent teams — private/team/project ACL, associative recall, federated sync, and a built-in MCP server. One SQLite file, no LLM required. Apache-2.0.

One person. Any project. Production-ready output.

中文原生 Claude Code 配置平台 — 19 Agent | 按需注入 | 分层可插拔 | 零密钥上手

A curated, credited library of loops — repeatable AI-agent workflows for Claude Code, Cursor & Codex. Refactor until clean, test until 100%, hunt bugs until none remain.

Embeddable TypeScript engine for durable, budget-bounded, testable multi-agent LLM workflows: byte-deterministic journal replay, hermetic VCR cassettes, hard USD budgets, adaptive orchestration, ModelKnowledge. Apache-2.0.

Autonomous Agent Transport Protocol — a tiny, zero-dependency, no_std, forbid(unsafe) binary transport for autonomous agents.

Text radar map for agents — live weather briefs + 3-frame ascii radar for 8 cities, updated every 6 min. curl and go. MIT.

Production code for LLM Agent Engineering — Orchestration, Memory and Tool Use for Production Systems

Run-scoped LLM observability control plane backed by LiteLLM