返回目录

open-managed-agents

维护状态: 活跃

openma-ai/open-managed-agents

开源实现 Claude 托管智能体 API 的自托管运行时,兼容 Claude Tag 风格,可运行于 Cloudflare Workers 或 Node.js。

前往 GitHub项目主页
$ git clone https://github.com/openma-ai/open-managed-agents.git && cd open-managed-agents && cp .env.example .env

265

星标

40

Fork

TypeScript

语言

Apache-2.0

许可证

2026-04-10

创建于

2026-09-09

最近推送

Apache-2.0 自托管 Agent 运行平台,兼容 Claude Managed Agents API,提供会话、沙箱、记忆库与 MCP 工具;README 未记载 DeepSeek Harness 专属集成。

DSH 适配

生态相关

自动推断

安全审计

未审计

最后核验

2026-08-21

许可证

Apache-2.0

01它能帮你完成什么?

  • Self-host a managed-agent runtime that runs agents with durable sessions, sandboxes and built-in tools

    A running /v1/agents + /v1/sessions API with Console UI on port 8787 (Docker self-host in ~2 min or Cloudflare Workers deploy), verified via the /health endpoint

    Platform and infra engineers who want self-hosted, BYOK agent infrastructure under their own deployment boundary

  • Automate workflows by publishing agents into Slack, GitHub and Linear

    Agents acting as real teammates — assignable on issues, @mentionable, replying in threads — with per-publication capability gates and isolated bot identities

    Engineering and product teams that want agent-driven workflow automation inside the tools they already use

  • Give long-running agents persistent, versioned memory

    Memory stores mounted into the sandbox at /mnt/memory/<store_name>/, accessed with standard file tools, with version history, redaction and CAS updates

    Builders of long-lived agents that need durable cross-session memory under their own deployment

02如何接入 DeepSeek Harness?

前置条件

  • Docker (self-host path) — the README quick start runs `docker compose up -d`
  • Two locally generated secrets: BETTER_AUTH_SECRET (openssl rand -hex 32) and PLATFORM_ROOT_SECRET (openssl rand -base64 32)
  • Cloudflare path only: Workers Paid plan (required for Durable Objects + Containers)

安装步骤

  1. 01

    $ git clone https://github.com/openma-ai/open-managed-agents.git && cd open-managed-agents && cp .env.example .env

  2. 02

    Set BETTER_AUTH_SECRET and PLATFORM_ROOT_SECRET in .env; optionally ANTHROPIC_API_KEY so the first agent can run without a Model Card

  3. 03

    docker compose up -d (SQLite + LocalSubprocess sandbox, default) — or docker compose -f docker-compose.postgres.yml up -d for the Postgres backend

验证接入成功

  • curl localhost:8787/health returns {"status":"ok","backends":{"db":"sqlite ..."}, ...}; the Console UI opens on http://localhost:8787
  • Smoke test the harness end-to-end: POST /v1/agents to create an agent, POST /v1/sessions to start a session, then POST a user.message event

03DSH 适配与能力边界

DSH 适配生态相关

No DeepSeek Harness integration is documented in the README; OMA is a self-hosted, Claude Managed Agents API-compatible meta-harness platform that runs agents and their workflows as standalone infrastructure

  • Claude Managed Agents-compatible API

    existing clients/SDKs of the Claude Managed Agents APIsame /v1/agents, /v1/environments, /v1/sessions, /v1/vaults endpoints and event types, drop-in compatible

  • Built-in agent toolset (agent_toolset_20260401)

    an agent configured with the built-in toolsetbash, read, write, edit, glob, grep, web_fetch, web_search, cron-style scheduling, and opt-in headless browser

    bash executes commands in the sandbox; web_fetch and web_search make outbound network requests (web_search requires TAVILY_API_KEY)
  • Encrypted vaults with outbound credential injection

    vaults holding static_bearer / mcp_oauth / cap_cli credentials bound to request hostsreal credentials injected at the network layer on matching outbound requests — tokens never enter the sandbox

    credentials are AES-GCM encrypted at rest under PLATFORM_ROOT_SECRET; each forward emits a structured op:"mcp_proxy.forward" log
  • MCP server registry

    up to 20 MCP servers per agent — HTTP/SSE (hosted) or stdio (npm/PyPI packages)upstream tools surfaced to the model as mcp__<server>__<tool>

    stdio servers are spawned inside the sandbox container (talks to 127.0.0.1:port/sse)

04适合谁?何时不该用?

适合

  • Platform and infra engineers who want self-hosted, BYOK agent infrastructure under their own deployment boundary
  • Engineering and product teams that want agent-driven workflow automation inside the tools they already use
  • Builders of long-lived agents that need durable cross-session memory under their own deployment

不适合

  • PLATFORM_ROOT_SECRET is mandatory to boot and encrypts all credentials, model-card API keys and integration tokens at rest — losing it makes every encrypted row unreadable, so it must be backed up.
  • The Cloudflare deployment path requires a Workers Paid plan because it relies on Durable Objects + Containers; the free self-host (Docker/Node) path is the alternative.
  • The default sandbox provider is subprocess with no isolation; an isolated backend (litebox, daytona, e2b or boxrun) should be used when running untrusted agents.

05兼容性、维护与安全提示

  • PLATFORM_ROOT_SECRET is mandatory to boot and encrypts all credentials, model-card API keys and integration tokens at rest — losing it makes every encrypted row unreadable, so it must be backed up.
  • The Cloudflare deployment path requires a Workers Paid plan because it relies on Durable Objects + Containers; the free self-host (Docker/Node) path is the alternative.
  • The default sandbox provider is subprocess with no isolation; an isolated backend (litebox, daytona, e2b or boxrun) should be used when running untrusted agents.
2026-04-102026-08-19@openma/cli@0.5.0

Apache-2.0 · actively maintained (last push 2026-08-19, latest release @openma/cli@0.5.0)

06常见问题

它和 DeepSeek Harness 是什么关系?如何接入?

README 未记载与 DeepSeek Harness 的直接集成。OMA 本身是运行 harness 的平台:用 SDK 的 defineHarness 编写 harness,通过 `oma deploy --harness my-harness.ts --agent <id>` 部署,平台负责提供会话、沙箱、工具、事件日志与崩溃恢复。

自托管需要什么前置条件?

需要 Docker,以及两个本地生成的密钥:BETTER_AUTH_SECRET(签发控制台会话)和 PLATFORM_ROOT_SECRET(静态加密凭据,务必备份)。Cloudflare 部署路径还需要 Workers 付费计划(Durable Objects + Containers)。

如何验证安装成功?

运行 `curl localhost:8787/health`,返回 `{"status":"ok",...}` 即成功,控制台 UI 同在 8787 端口。README 还提供端到端冒烟测试:POST /v1/agents 创建 Agent、POST /v1/sessions 开启会话、再发送一条 user.message 事件。

凭据和密钥存放在哪里?

凭据在 PLATFORM_ROOT_SECRET 之下以 AES-GCM 加密静态存储;令牌永不进入沙箱,由出站解析器在网络层剥离入站认证头并注入真实凭据。丢失 PLATFORM_ROOT_SECRET 会导致所有加密数据不可读。

支持 MCP 工具吗?

支持。每个 Agent 最多注册 20 个 MCP 服务器(HTTP/SSE 托管式或 stdio 包,stdio 在沙箱容器内启动),上游工具以 `mcp__<server>__<tool>` 形式暴露给模型。

08数据与来源

  • 自动推断github.com92556f718f74…

    **Open-source alternative to Claude Managed Agents** — and a foundation for open-source, self-hosted Claude Tag-style ag…

  • 自动推断github.com92556f718f74…

    Drop-in compatible with the Claude Managed Agents API; runs on Cloudflare Workers + Durable Objects, or `docker compose…

页面基于项目公开文档、仓库元数据和 DSH Plugins 的结构化解析生成;最后核验于 2026-08-21。发现错误?提交更正。

🏆

最佳 DeepSeek Harness 插件

从全目录挑出的 12 个值得优先安装的插件,覆盖各个分类。

DSH Plugins 是独立的 DeepSeek Harness 插件市场,与 DeepSeek 官方无关,也不代表官方背书。第三方插件未经安全审计,安装前请审查源码。

每周获取最新的 DeepSeek Harness 插件,绝不滥发。