v0.0.0 · MIT
DeepSeek Harness adapter for Qwen Token Plan CN with Responses tools, GLM Chat routing, and a versioned official catalog
v1.5.3 · MIT
dsh「专家团」bundle:一句自然语言组建角色化多智能体「数字员工」团队,按九阶段门控流水线协作交付,实现者直接改代码并产出持久工件;带 live 团队浮层。 · Role-based multi-agent expert team for DeepSeek Harness: one sentence in, a staged and gated team delivery out.
v0.10.0 · MIT
记忆核心(Memory Eternal):自研的 DeepSeek Harness 记忆插件,不移植任何既有记忆框架——对话结束后自动沉淀知识卡到本地 Markdown Vault(自研去重、自研 CJK 检索、可 git 管理),设置页提供图形化知识库(统计 / 搜索 / 知识图谱 + 侧边栏一键弹窗),Agent 通过 memory_recall 工具按需召回历史上下文。零人工干预。
— · MIT
Portable skills, agents, hooks, and Pi extensions for Claude Code, Codex CLI, Copilot, Cursor, Grok, and Pi.
— · MIT
Plugins for the OutSystems remote MCP.
— · MIT
Use Cursor CLI from Claude Code to delegate coding tasks to Composer 2.5+ and other Cursor models.
v0.1.0 · MIT
Multi-agent codebase review for PRs, CI, and downstream fork syncs.
v1.1.13 · MIT
The linter for your agent harness. Works with Claude Code, Codex, and Cursor.
v3.4.0 · MIT
Project continuity for Claude Code and Codex: a roadmap beside your code, grounded handoffs, and clear task status.
v1.79.0 · MIT
Use Claude and Antigravity subscriptions with Pi, OpenCode and other coding clients. Local API bridge, usage dashboard and optional Mac app.
v2.13.0 · Apache-2.0
An open-source, local-first writing workspace where you can write with Claude Code and Codex, drawing on your own sources and past work.
v3.13.1 · MIT
Claude-Code-style dynamic workflows for Pi — fan a task out across 100s of subagents with real model routing, token/cost accounting, resume, git-worktree isolation, an interactive /workflows TUI, and a real /deep-research.
v4.12.4 · MIT
Structured project lifecycle plugin for Claude Code — from idea to production with discipline, parallel agents, and quality gates.
v2.39.13 · Apache-2.0
The deterministic agent-integrity gate. One ruleset, evaluated on the actual diff/commands as a verdict, enforced everywhere a change can be made.
v0.5.0 · MIT
把对话里说过的重要事情,变成持续可跟进的计划。 为 deepseek-harness 打造的个人助手:从对话中整理事项、跟踪变化,并在需要时提醒你。
— · MIT
A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.
v0.1.44 · MIT
ACRYL - Agent Context Relay Yielding Lifecycles. One persistent workspace, one canonical context, any coding agent.
v0.0.0 · Apache-2.0
Toward Autonomous Scientific Discovery
— · Apache-2.0
Run Codex and Cursor as background workers inside Claude Code. Reviews, tasks, and rescues with tracked jobs, live progress, and session handoffs.
v1.131.6 · MIT
Phone control panel for local Conductor agents. Reads ride SQLite + git; prompts ride Conductor's own dispatch path.
v0.14.3 · MIT
Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨
v1.2.1 · MIT
Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.
v1.13.4 · MIT
Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.
v0.13.2 · MIT
The Fintech Builder algorithm library — canonical, cross-language reference implementations of market-data, corporate-action, index, breadth, candlestick and technical-indicator algorithms, exposed as provider-agnostic subpath modules.