handoff-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@handoff-mcpsave our progress and next steps for the JWT auth task"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TaskHandoff
DeepSeek-friendly long-task project memory & cross-session handoff for coding agents.
长任务做到一半换会话 / 上下文被压掉 / 换模型 —— Agent 忘了目标、决策和下一步。
TaskHandoff 把状态写进仓库.handoff/:任何能读项目文件的 Harness 都能恢复任务状态,并拿到结构化的下一步上下文。
「能恢复」有自动化测试证据;「LLM 一定把活干完」仍需 harness 级评测。
Repo | |
Skill name |
|
CLI |
|
MCP |
|
DSH | Skill + CLI + MCP 同一 |

init→save --auto→recall --brief→doctor
怎么录 / 怎么重渲:examples/how-to-record-gif.md
Continuity evidence(跨会话可恢复)
命令 | 角色 |
| 完整 CI 证据(hooks 闭环、 |
| 约 15 秒 smoke demo(显式 save → recall only;不覆盖 hooks/--auto/toy) |
# Full evidence (what CI runs via pytest -q):
pytest tests/test_continuity.py -q
# Quick human-readable smoke (not a substitute for the suite):
python scripts/continuity_proof.pyThe suite proves disk-level continuity across independent processes.
LLM execution quality still requires harness-level evaluation.
Details: examples/continuity-proof.md
30 秒心智模型
会话 A 干到一半 → handoff save [--auto] → 写入 .handoff/
新开会话 / 换模型 → handoff recall --brief → 恢复 goal + next 1..3
(Agent 可据此继续;执行成败取决于模型/harness)文件 | 作用 |
| 长期记忆(偏好、架构、坑) |
| 上一会话状态 + 下一步 3 条 |
| 结构化待办与决策日志 |
Related MCP server: SloplessCode
安装(推荐最低完整版)
需要 Python 3.9+,零第三方运行时依赖。
git clone https://github.com/sutongwuyanzu/TaskHandoff.git
cd TaskHandoff
pip install -e .
# 验证
handoff --version
# 或
python -m taskhandoff --versionMCP(stdio,零额外依赖)
pip install -e .
handoff-mcp
# 或
python -m taskhandoff.mcp_server把 stdio server 配进 Claude Desktop / Cursor 等(示例:examples/mcp-config.sample.json,说明:references/mcp.md)。
不装包也可以用 CLI:
python scripts/handoff_cli.py init --root /path/to/project装成 Agent Skill
# 一键脚本(推荐)— 在仓库根目录执行
# Windows PowerShell:
powershell -ExecutionPolicy Bypass -File scripts/install-skill.ps1
# macOS / Linux:
bash scripts/install-skill.sh
# 或手动
cp -r TaskHandoff ~/.claude/skills/task-handoff装好后对 Agent 说:交接 / 接着做 / handoff。SKILL.md 是剧本;handoff CLI / MCP 是执行层。
快速演示:init → save → recall
在任意项目里:
cd /path/to/your-app
# 1) 初始化(每个仓库一次)
handoff init --root .
# 2) 会话结束前交接(推荐 --auto:自动带上 git 变更/最近 commit)
handoff save --root . --auto \
--goal "Ship JWT auth" \
--done "Middleware scaffolded" \
--decision "Refresh token in httpOnly cookie" \
--next "Finish refresh endpoint" \
--next "Add 401/403 tests" \
--next "Document env vars" \
--memory-delta "Auth: access token memory-only; refresh httpOnly cookie"
# 3) 新会话只读 brief(短、稳、给 Agent 直接开干)
handoff recall --root . --brief
# 4) 需要全文时
handoff recall --root . --budget 2500
# 5) 健康检查(含密钥扫描)
handoff doctor --root .
handoff status --root .自然语言(Agent 读 SKILL.md)
你说 | Agent 应做 |
交接 / handoff |
|
接着做 / continue / resume |
|
记住我们用 pnpm |
|
handoff 状态 |
|
示例交接包
完整样例见 examples/filled-LATEST.md。
recall --brief 输出形态:
# Resume brief (TaskHandoff)
- project: `your-app`
- goal: Ship JWT auth
- next:
1. Finish refresh endpoint
2. Add 401/403 tests
3. Document env vars
- instruction: Execute next action #1 now. ...安全
默认拒绝把疑似密钥写进 handoff(GitHub PAT、JWT、私钥块、常见
api_key=等)误报时才用:
handoff save ... --allow-secrets(不推荐)handoff doctor会扫描已有LATEST.md
目录结构
TaskHandoff/
SKILL.md # Agent skill 剧本
taskhandoff/ # 可安装 Python 包(CLI)
scripts/handoff_cli.py # 兼容入口
templates/ # MEMORY / handoff 模板
references/ # schema + DSH 接入说明
examples/ # 示例流程与 filled handoff
tests/ # pytest 契约测试
APPLY.md # DSH 内测报名文案
pyproject.toml项目内生成:
your-app/.handoff/
config.json
MEMORY.md
todos.json
decisions.jsonl
handoffs/LATEST.md
handoffs/LATEST.json契约说明:references/schema.md
DeepSeek Harness (DSH)
类型:Skill + CLI + MCP(同一
.handoff/契约)无私有二进制格式:纯 Markdown + JSON
Token 预算:
recall --budget/--brief发布日接入计划:references/deepseek-notes.md
报名文案:APPLY.md
更多示例
真实风格交接包:examples/filled-LATEST.md
会话 Hook 样例:examples/hooks/(SessionStart → recall,SessionEnd → save)
本仓库自用 dogfood:
.handoff/(handoff recall --root . --brief)
开发与测试
pip install -e ".[dev]"
pytest -q
handoff info --root .CI:GitHub Actions 在 main 上跑 Python 3.9 / 3.12。
设计原则
Portable — 状态在仓库里,不绑云
Token-thrifty — 固定章节 + brief
Harness-agnostic — Claude Code / Codex / 未来 DSH
Safe by default — 密钥扫描
Roadmap
可安装 CLI(
handoff)save --auto(git + 上次 handoff)recall --brief固定复述密钥拒绝写入 +
doctorpytest 契约测试
纯 stdlib MCP server(同一
.handoff/契约)GitHub Actions CI + skill 安装脚本 + 仓库 dogfood
会话 hook 样例(Claude Code / generic / DSH 映射)
README 终端 GIF(
assets/terminal-demo.gif+ 可重渲脚本)
License
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityCmaintenanceA portable MCP server that provides a shared persistent working state for AI coding agents, managing tasks, plans, notepads, memory, and project rules across different tools like Claude Code, OpenCode, and Cursor.695MIT
- Alicense-qualityBmaintenanceProvides operational continuity for AI coding agents, preserving task state, decisions, checkpoints, and project context across sessions and model switches via MCP.1Apache 2.0
- Alicense-qualityCmaintenanceAn MCP server that gives your agent a persistent project brain: vision, architecture decisions, conventions, roadmaps, and automatic session handoff.486MIT
- Flicense-qualityAmaintenanceLocal MCP server that lets your AI coding agent query its own cross-tool project history - file/command freshness, past test failures, cost & token spend, cache status, and session handoff - over stdio, 100% local, no telemetry.37
Related MCP Connectors
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
StremAI MCP: shared memory for AI coding agents. Connected agents can recall. OAuth + local stdio.
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sutongwuyanzu/TaskHandoff'
If you have feedback or need assistance with the MCP directory API, please join our Discord server