Apache-2.0, self-hosted Claude Managed Agents API implementation — a meta-harness that runs agents with sessions, sandboxes, memory and MCP tools; no DeepSeek Harness integration is documented in the README.
DSH integration
Ecosystem-related
Inferred
Safety audit
Unaudited
Last verified
2026-08-21
License
Apache-2.0
01What can it help you accomplish?
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
02How to install into DeepSeek Harness
Prerequisites
- 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)
Installation steps
- 01
$ git clone https://github.com/openma-ai/open-managed-agents.git && cd open-managed-agents && cp .env.example .env
- 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
- 03
docker compose up -d (SQLite + LocalSubprocess sandbox, default) — or docker compose -f docker-compose.postgres.yml up -d for the Postgres backend
Verify the integration
- 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 integration and capability boundaries
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 API→same /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 toolset→bash, 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 hosts→real 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" logMCP 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)
04Who is it for? When not to use it?
Good for
- 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
Not for
- 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.
05Compatibility, maintenance and safety notes
- 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.
Apache-2.0 · actively maintained (last push 2026-08-19, latest release @openma/cli@0.5.0)
06Frequently asked questions
How does Open Managed Agents relate to an agent harness like DeepSeek Harness?
The README does not document a direct DeepSeek Harness integration. OMA is itself a platform that runs harnesses: write one with defineHarness from the SDK, deploy it via `oma deploy --harness my-harness.ts --agent <id>`, and the platform supplies sessions, sandboxes, tools, the event log and crash recovery.
What do I need to self-host it?
Docker plus two locally generated secrets: BETTER_AUTH_SECRET (signs Console sessions) and PLATFORM_ROOT_SECRET (encrypts credentials at rest — back it up). The Cloudflare path additionally requires a Workers Paid plan for Durable Objects + Containers.
How do I verify the install works?
Run `curl localhost:8787/health` — a `{"status":"ok",...}` response means success, and the Console UI opens on the same port. The README also ships an end-to-end smoke test: create an agent via POST /v1/agents, start a session, and send a user.message event.
Where do credentials and secrets go?
They are AES-GCM encrypted at rest under PLATFORM_ROOT_SECRET. Tokens never enter the sandbox — an outbound resolver strips inbound auth headers and injects the real credential at the network layer. Losing PLATFORM_ROOT_SECRET makes every encrypted row unreadable.
Does it support MCP tools?
Yes — up to 20 MCP servers per agent, over HTTP/SSE (hosted servers) or stdio (spawned inside the sandbox container). Each upstream tool surfaces to the model as `mcp__<server>__<tool>`.
07Related DSH workflows
openviking
by volcengine
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
colleague-skill
by titanwings
Turn memories and knowledge into warm, reusable agent skills — a skill generator for digital companions in the AI persona era.
archify
by tt-a1i
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
learn-harness-engineering
by walkinglabs
Harness engineering beginner tutorial, from 0 to 1
08Data and sources
**Open-source alternative to Claude Managed Agents** — and a foundation for open-source, self-hosted Claude Tag-style ag…
Drop-in compatible with the Claude Managed Agents API; runs on Cloudflare Workers + Durable Objects, or `docker compose…
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.