> **A TypeScript Framework for Building Tool-Using AI Agents**
AgentLoop binary for linux-x64
Drop-in OpenAI SDK wrapper for AgentLoop. Adds memory retrieval and turn logging to every chat.completions.create call.
Drop-in Anthropic SDK wrapper for AgentLoop. Adds memory retrieval and turn logging to every messages.create call.
JavaScript / TypeScript SDK for AgentLoop — middleware that turns human corrections into searchable memory for your agent.
AgentLoop binary for darwin-arm64
AgentLoop binary for windows-x64
Official SDK for the AgentLoop Agentic Marketing Network
AgentRuler SDK — AgentLoop core with Node.js backend adapter, permission system, and full toolbar settings API.
AI agent that monitors chat platforms and responds using Claude Code
AgentLoop integration for LangChain — earn up to 70% revenue share when your agent recommends relevant products.
AI-powered autonomous coding agent
OpenClaw memory plugin: long-term memory via Alibaba Cloud CMS AgentLoop Memory API .
Zhin AI Agent — session, ZhinAgent, init; composes @zhin.js/core providers and tools
TWZRD on Solana: Liquid Attention protocol instruction builders. For agent trust + x402 receipts (the active product), see twzrd-agent-intel and intel.twzrd.xyz.
General-purpose agent with transport abstraction, state management, and attachment support
Agentic loop system with tool execution for LLMs
PulSeed is a lifelong personal agent that remembers your goals, watches the world with you, and keeps helping move your life forward.
CLI for Agent Task Service - task orchestration between AI agents and humans
AI-powered terminal coding assistant
YUAN Agent Core Runtime
AI-first coding agent harness — model-agnostic, context-intelligent, self-improving. CLI + Web app.
Agentic loop system with tool execution for LLMs
OpenJaw Agent — Autonomous desktop AI assistant for the terminal. Rich Ink TUI, 100+ tools, multi-channel bridges (Telegram, Feishu, Teams, WeChat). Standalone, no MCP server required.
Agentic loop for Rust — multi-turn tool dispatch, streaming, and conversation management over any LLM provider
Rust agent framework based on harness-engineering principles (Lopopolo, Böckeler). Facade re-exporting the public surface of the harness-rs-* crates.
Deterministic + agent hybrid state-machine executor for harness-rs. Stripe-Minions-style with branch-on-failure retries.
Command-line interface for harness-rs — new, skills validate/list/lint/export, trace, mcp serve.
Five-stage progressive context compactor for harness-rs — DefaultCompactor (structural) and ModelBackedCompactor (semantic).
Default World runtime (Tokio process runner, system clock, in-memory KV) and Context helpers for harness-rs.
Core traits and types for the harness-rs agent framework: Model, Tool, Guide, Sensor, Hook, Compactor, Skill, plus Context, World, Block, Event, FixPatch and 27 lifecycle events.
Optional standalone scheduler for the harness-rs agent framework. Runs declarative TOML-configured jobs (daily / weekly / interval / cron) that invoke any shell command — typically a harness-rs-built agent binary.
HookBus for harness-rs. Dispatches 27 lifecycle events with Allow/Deny/Inject/Mutate semantics. Optional OpenTelemetry feature.
ReAct agent loop, subagent isolation, and session record/replay (JSONL) for the harness-rs framework.
Procedural macros for harness-rs: #[skill], #[tool], #[guide], #[sensor], #[hook]. agentskills.io-compliant registration via inventory.
MCP (Model Context Protocol) stdio server exposing the harness-rs tool registry to Claude Code, Cursor, and Codex.