Apache-2.0 autonomous AI research platform (literature to reviewed paper) deployed via Docker Compose; its read-only MCP server connects it to coding agents as a DeepSeek Harness ecosystem companion.
DSH integration
Ecosystem-related
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
Apache-2.0
01What can it help you accomplish?
Run the full research lifecycle — literature survey, idea generation and review, GPU experiments, LaTeX paper writing, and paper review — as one platform
Cross-linked research wiki, scored and deduplicated ideas with Elo-ranked review, experiment runs with streamed logs and metric curves, multi-file LaTeX papers with live PDF preview, and citation-verified reviews
Research labs and AI research teams that want an autonomous AI-scientist platform covering the whole pipeline
Let agents run long experiments on lab GPU servers with self-verification and human gates
Automated experiment Voyages: study plan, compute-budget check, generated code, smoke test, streamed runs with live metric curves, and auto-iteration that repairs failures under a time budget
ML researchers who want agents to execute and iterate on real GPU servers under budgets and audit
Expose Polaris's research knowledge to external coding agents via MCP
An MCP server (Streamable HTTP and stdio) of read-only tools over literature, knowledge, project state, manuscripts, and external search
Users of coding agents (Claude Code, Codex, Cursor) who want research context inside their agent workflow
02How to install into DeepSeek Harness
Prerequisites
- Docker and Docker Compose only — the README says no local Python, Node, or database is needed for the recommended Docker Compose setup
- LLM provider keys and secrets configured in .env
Installation steps
- 01
Run `cp .env.example .env` and set provider keys and secrets
- 02
Run `make dev` to start the full stack via docker compose with hot reload (frontend at http://localhost:5173, backend API docs at http://localhost:8000/docs)
- 03
Production alternative: deploy pre-built images — set POLARIS_ENV=prod and POLARIS_IMAGE_TAG in .env, run `docker compose --env-file .env -f docker/docker-compose.yml pull`, then `up -d`, then `docker compose -f docker/docker-compose.yml exec api alembic upgrade head` (required on first run)
Verify the integration
Not specified by the author
03DSH integration and capability boundaries
DSH-ecosystem AI research platform (tagged dsh-plugin on GitHub): run Polaris as a standalone web app via Docker Compose; its MCP server exposes read-only research tools to external coding agents
Voyage agent core
any long-running research task (literature backfill, experiment run, paper drafting)→resumable, auditable runs with a persisted planning → executing → verifying loop that resumes from checkpoint after a crash
retains every plan, action, and verdict, replayable in the UI; auto-pauses when budgets are exceededResearch Wiki (compile, don't retrieve)
papers from OpenAlex, Semantic Scholar, and arXiv→one cross-linked wiki per paper shared platform-wide (TL;DR, method, reusable ideas, concept backlinks), research digests, and Obsidian vault sync
queries external literature APIs (OpenAlex, Semantic Scholar, arXiv) and writes wiki/Obsidian artifactsExperiment Lab over SSH
per-user, Fernet-encrypted SSH credentials to the lab's GPU servers→planned, budget-checked experiment runs with streamed logs, live metric curves, generated figures, and a file-based memory kept across steps
writes and runs code on remote GPU servers under gated remote writes, command allow/deny lists, and triple budget capsMCP tool layer
Polaris project data (literature, knowledge, project state, manuscripts)→an MCP server (Streamable HTTP and stdio) exposing read-only tools to Claude Code, Codex, and Cursor, with a self-check playground
exposes project data over the network (Streamable HTTP / stdio); strictly read-only and project-isolated
04Who is it for? When not to use it?
Good for
- Research labs and AI research teams that want an autonomous AI-scientist platform covering the whole pipeline
- ML researchers who want agents to execute and iterate on real GPU servers under budgets and audit
- Users of coding agents (Claude Code, Codex, Cursor) who want research context inside their agent workflow
Not for
- The README does not document running inside DeepSeek Harness (dsh): Polaris is deployed as a standalone web app via Docker Compose; its connection point to external agents is a read-only MCP server documented for Claude Code, Codex, and Cursor.
- The recommended deployment is a full multi-container stack (PostgreSQL 16 with pgvector, Redis 7, API, worker, frontend), and the first-run `alembic upgrade head` migration is mandatory since Postgres tables are not auto-created.
05Compatibility, maintenance and safety notes
- The README does not document running inside DeepSeek Harness (dsh): Polaris is deployed as a standalone web app via Docker Compose; its connection point to external agents is a read-only MCP server documented for Claude Code, Codex, and Cursor.
- The recommended deployment is a full multi-container stack (PostgreSQL 16 with pgvector, Redis 7, API, worker, frontend), and the first-run `alembic upgrade head` migration is mandatory since Postgres tables are not auto-created.
- Desktop builds are neither signed nor notarized: macOS needs `xattr -dr com.apple.quarantine`, Windows SmartScreen requires Run anyway, and the Linux AppImage needs extra system libraries.
Apache-2.0 · actively maintained (latest release v0.3.8, 2026-08-17)
06Frequently asked questions
How does Polaris connect to DeepSeek Harness?
The README does not document a native dsh integration. Polaris runs as its own web application deployed with Docker Compose; its connection point to external coding agents is a read-only MCP server (Streamable HTTP and stdio), documented for Claude Code, Codex, and Cursor.
What do I need to run Polaris?
Docker and Docker Compose are enough for the recommended setup — no local Python, Node, or database. Copy `.env.example` to `.env`, set your LLM provider keys and secrets, then run `make dev` (or deploy the pre-built Docker Hub images for production).
Can agents run real experiments on GPU servers?
Yes. The Experiment Lab uses per-user Fernet-encrypted SSH credentials, plans the study, passes a compute-budget check, writes and runs code with streamed logs and live metric curves, and auto-iterates under gated remote writes, command allow/deny lists, and triple budget caps.
What is a Voyage?
Every long task is a Voyage: a persisted, resumable, human-gated agent run driven by a Navigator (planning), Helm (execution), and Sextant (self-verification) loop. If a worker crashes, it resumes from its last checkpoint, and budgets auto-pause the run when exceeded.
Is the desktop app safe to install?
The builds are neither signed nor notarized, so each OS asks once: on macOS run `xattr -dr com.apple.quarantine /Applications/Polaris.app`, on Windows choose More info → Run anyway, and on Linux the AppImage needs libnss3, libgtk-3-0, and libasound2.
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
is exposed both internally to the agent loop and externally as an **MCP server** (Streamable HTTP and stdio) for Claud…
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.