Explore

O(1) prompt footprint for long-horizon agents. The SKILL.state paper (arXiv:2608.26263) reimplemented — eq. 8 reproduces exactly, 82.5x at 60 files. 100% coverage.

Node.js·MIT·★ 2·Few stars·No key

Dev skills I use day to day in agentic engineering, focused on multi-agent-driven work modes and long-horizon autonomous tasks.

Skill·Link only·★ 12

Long-horizon conversational memory compaction & episodic anchor extractor (Mem0 / LangMem)

Skill·Link only·★ 8

A reliability layer for long-running AI agents - progress survives crashes, context loss, and executor changes without relying on chat history. Ships as a normative spec, an installable agent skill, a

Skill·MIT·★ 3·Few stars·No key

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

Skill·MIT·★ 145k·No key

OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against m

Skill·AGPL-3.0·★ 245·No key

Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.

Skill·Apache-2.0·★ 368·No key

J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.

Skill·Apache-2.0·★ 3.0k·No key

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the a

Skill·MIT·★ 71·No key

A simulation benchmarking platform for evaluating generalist robot policies

Skill·Apache-2.0·★ 567·No key

Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eage

Node.js·MIT·★ 501·No key

Build agent that uses 80% less token and delivers better results.

Skill·AGPL-3.0·★ 657·No key

Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results

Python·MIT·★ 114·No key

Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief revision, selective forgetting, and reproducible benchmarks.

Python·MIT·★ 15·No key

TUI framework and developer productivity apps in Rust 🦀

Skill·Apache-2.0·★ 486·No key

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Skill·MIT·★ 293·No key

A Codex Agent Skill for long-horizon reasoning, context synthesis, root-cause persistence, verification, and completion discipline.

Skill·MIT·★ 8·No key

All-in-one, unified harness. Increasing productivity, and accuracy both at the same time. https://pi.dev/packages/@pi-unipi/unipi?name=unipi

Node.js·MIT·★ 71·No key

Turn any repository AI-first and run resumable, long-horizon Deep Work Plans with any coding agent — an installable, MIT-licensed agent skill.

Skill·MIT·★ 23·No key

Lightweight agent orchestration dev tool that lives in your repo

Skill·Apache-2.0·★ 294·No key

An open, thin, model-agnostic harness for long-horizon autonomous AI research. Built on Goose.

Skill·Apache-2.0·★ 13·No key

Long-horizon AI harness you actually own: one static Go binary, one persona, any OpenAI-compat LLM (Ollama, Gemini, Claude, ChatGPT), MCP tools, chat via Telegram/Discord/Slack. Outbound-only — no das

Go·MIT·★ 4·Few stars·No key