Autonomous AI agents that perform tasks independently
Git for agent trajectories - branch, diff, and bisect LLM agent runs, backed by real re-execution.
we-are-singular
Agent Markup Language - an asynchronous TypeScript and JSX runtime for composing provider-agnostic agent workflows.
ardhaecosystem
The Fable Method: a structured problem-solving loop that gives any model Fable 5 grade thinking. Four Hermes Agent skills (think/act/prove/grow) + adversarial eval.
...morekartikmehta8
NT — a language for agent ecosystems
shimo4228
The Agent Knowledge Cycle as a single behavioral rules file — install all six phases without the six standalone skills.
shimo4228
The Authorship Strategy framework as a single always-loaded behavioral rule — the deterministic counterpart to the authorship-strategy-skill. Part of the shimo4228 research ecosystem.
...moregulagala001
有记忆的白板智能体:PenEcho 手写白板 ↔ 常驻 pi agent(会话记忆+persona+工作区文件)。电脑端双击 app + 安卓单 APK,WiFi 扫码配对,多项目文件夹同步,项目内多会话。
nhannvt
AI Application Discovery Protocol (AADP) — specification, schemas, validator, reference client and conformance suite
c4ccz
OMEGA MASTER v10.0 — Ultimate Autonomous Pentest Engine by @c4ccz. 8 Collaborative AI Agents, 5000+ Paths, 3000+ Payloads, Deep Correlation, Attack Chains, Browser Automation.
...moredavidokonji
Stream a running Android emulator or device to the browser and drive it (tap/swipe/type/keys) — for humans and AI agents. TypeScript + bun.
...moreNakagai edge: the connector runtime that holds your broker credentials
Ranajit Dhar <[email protected]>
One interface for resilient, multi-provider AI generation.
Manmit <[email protected]>
A powerful agentic AI coding CLI built with Python and Rich TUI
Give your OpenAI Agents SDK agent a June memory — wrap any Session to mirror conversations into a searchable, cited June knowledge canvas, add a memory-search tool, and backfill existing session databases.
...moreIncident Commander Contributors
Multi-agent AI incident commander for Kubernetes — correlates deploys, logs, metrics, and suggests rollback with human approval
...moreLocal shared memory for coding agents (Claude Code, Cursor, Codex, Copilot, Kimi, Goose) plus opt-in token-savings proxy. Fire and forget — no Memor API key.
...morelangchain-openapi contributors
Convert OpenAPI specifications into native, production-grade LangChain tools.
awslabs
Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions
belarusian
A web-based Stoic philosophy dialogue tool that reads from Marcus Aurelius' Meditations to help users reflect on present-moment challenges through AI-powered 'What if?' scenarios.
...morePan-Chera
MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute
Standalone workflow execution SDK for A2A-T multi-agent orchestration
Contract-bounded autonomy for LLM agents: five small primitives that make an agent safe to leave alone.
Role-boundary preservation and identity-drift detection for autonomous LLM agents.
talkersoft
Agent Arcade — voice-driven control for your AI agents (Electron UI + a shared Go dictation daemon, NDJSON over a local socket).
...more