— · Apache-2.0
88 installable open-source Agent Skills for research, social intelligence, marketing, and business workflows—compatible with Codex, Claude Code, Cursor, Gemini CLI, and DeepSeek Harness.
v3.79.0 · MIT
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.
v0.26.0 · MIT
A toolkit for frontier forecasting.
v1.7.0 · Apache-2.0
Chrome DevTools for coding agents
v1.0.0 · MIT
Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill(原同事 Skill).
v0.4.5 · Apache-2.0
Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)
v4.0.0-rc.4 · MIT
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati
v1.0.0 · MIT
Prompt as Code | GPT-Image2 工业级提示词引擎与模板库,530+ 个案例逆向工程,20+ 套工业级模板,并提炼出Skills,持续更新中
v1.1.13 · MIT
The linter for your agent harness. Works with Claude Code, Codex, and Cursor.
— · MIT
Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
v1.7.4 · MIT
DeepSeek Harness 的 ChatGPT/Codex 订阅插件:独立 OAuth、模型、真实额度、搜索与图片;无需 API Key 或 Codex CLI
— · Apache-2.0
Wenlan is a knowledge base for the AI-native age. Your AI agents capture what they learn, Wenlan keeps it current and distills it into source-cited wiki pages you can trust
v0.6.0 · AGPL-3.0
基于 DeepSeek Harness(DSH)的 SillyTavern 类文字游戏 Agent,支持候选项生成、对话式人物卡编辑、剧本模式与素材抽取。
v0.9.0 · MIT
管线管理内核(pipeline-kernel):单向任务链的任务板/台账/注册表/巡检/播种/打包/自愈。v0.9.0:rc.8 削薄工程(依赖对齐 rc.8、DshAgentRuntime 窄收口、webServer inject、domain/changed 统一失效、契约测试、CI 全量门禁;业务语义与入口冻结)。
v0.2.0 · MIT
Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.
v1.2.0-beta.2 · MIT
Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.
v3.0.0 · MIT
A pixel-art whale desktop companion for DeepSeek Harness — it swims while your agents work and taps the glass when an approval is waiting.
v0.13.0 · MIT
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
v0.2.19 · MIT
BitFun combines a high-performance agent runtime written in Rust with a polished desktop application. It pairs the depth of a Code Agent with open, general-purpose capabilities for work beyond software development.
— · Apache-2.0
When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned. Each check ships at measured zero false positives. 誠
— · MIT
AI made building cheap. It didn't make deciding cheap. Mycelium is a Claude Code harness that makes your agent run discovery and weigh evidence before it writes code. It earns the right to start. Built for software, courses, AI tools, and services.
v1.0.0 · MIT
Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.
v0.3.3 · MIT
把 dsh agent 接入微信、飞书等 20+ 聊天平台的聚合网关插件 | Aggregate IM gateway for DeepSeek Harness (dsh): connect your agents to WeChat, Feishu, Telegram, Discord & 20+ chat platforms
v0.1.2 · MIT
A lightweight, selectable smart-routing mode for DeepSeek Harness.