Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.

Enables agents to capture real browser interactions over CDP, compile them into deterministic replay scripts with parameterized inputs and stored secrets, and execute those workflows with real input events — no page re-reading or LLM in the replay loop. Also emits portable Agent Skills from recorded workflows.

Connects ChatGPT to local files, terminals, and the desktop through MCP with Chrome integration, letting users read and edit project files, run commands, and follow tool results as they arrive. It also adds durable multi-agent workers, Goal/Loop task tracking, mid-task corrections, and Compact & Resume for carrying session and worker history into a fresh chat.

Stata-MCP: A MCP server for integrating Stata into your agent loop with a safety-first design.

Make Claude Opus 4.8 behave like Claude Fable 5 — doctrine output style, drift-catching hooks, and an eval loop against golden Fable transcripts. Claude Code plugin.

A discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adversarial review, and a self-armed loop that keeps going until a real check passes. Built by Fable to make any Claude work like a careful senior engineer.

All-in-one workflow plugin—loops, swarms, and teams on Claude Code's Task System. All enforce exit criteria—swarm is faster with parallel queue execution, teams add contract-first coordination. Plan your way, execute your way. Optional: Beads for persistent memory, Ralph TUI for dashboard.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

High-frequency in-browser behavior tree execution engine for autonomous AI agents — 60Hz tick loops, reactive triggers, telemetry recordings, and safety guardrails.

Enables an AI agent to see and control the screen of an already-running macOS virtual machine over VNC, exposing four tools: screenshot, click, type_text, and key_press. This lets the agent drive a disposable VM's UI directly with its own model, without touching the real desktop or running a separate agent loop.

Oracle: standalone multichain agent control plane with an optional encrypted, loopback-only self-hosted signer.

oh-my-dsh：面向 DSH (DeepSeek Harness) 的插件生态——700+ 插件，只通过扩展接缝注册，不修改 agent-loop 骨架

Build Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.