基于 DeepSeek Harness（DSH）的稳定桌面端，集成Git、内置浏览器与记忆功能 | DeepSeek Harness desktop GUI with local workspaces, Git, browser and memory.

Use Claude Code like a Director, not a Programmer. MIT toolkit with Auto-Loop, guided setup, 27 commands, 14 agents, and 32 skills.

Local-first memory layer and protocol for AI coding agents. Markdown source of truth, SQLite FTS5 index, zero cloud.

Local deterministic memory and safety kernel for AI agents. Replaces vector RAG with STRATA, a cryptographically signed, append-only ledger, so every agent state carries proof. Uses causal_walk engine to trace execution failures back to their root cause, and Operator Lite to block destructive terminal terminal commands before they ever run

A lightweight persistent-memory companion for OpenCode & Claude

One session. Two commands. Full team. Zero meetings.

The best home for all your AI agents. Run them in the cloud or connect your own—with their context and tools in one place.

Model-controlled context blocks for DeepSeek Harness PTC mode

Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.

Public MCP server for the TokPortal API.

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code: tier routing (Sonnet 5 does the work), Requirements Ledger, enforced guard hooks, automatic teammate reaping

Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.

MCP server for PostgreSQL: local, Docker, RDS, Neon, Supabase, or behind an SSH bastion.

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.

DeepSeek Harness 的执行迷宫——看 Agent 真实怎么干活：迷宫时间轴 · 数据轨道 · 确定性执行分析 · 多会话对比 | The execution maze for DSH agents: maze timeline, per-step data tracks, deterministic execution analysis, multi-session comparison. Formerly dsh-trace-compare.

Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.

Local-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.

OKF-powered knowledge context for Claude Code — injects your project's knowledge base at every session

Mission control for long Claude Code runs: context and run progress at a glance, Autopilot handoffs, guardrails and a calm activity view, in the terminal and Claude Desktop.

A-Team MCP Server — build, validate, and deploy multi-agent solutions from any AI environment

Schema-as-code memory for AI agents in Obsidian: typed cards, entity dedup, link repair, update-in-place, and Ebbinghaus decay. Plain Markdown you own — a Claude Code skill.

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

Shared team knowledge, leaked-secret alerts, ranked code findings and tracked tasks, across every AI coding tool you use