# Octop (slim)

> Octop is a self-hosted assistant with multiple users and agents, a web dashboard, messaging channels and connectors. It can coordinate tasks across local workspaces, browser sessions and configured model providers.

- Full: https://www.anchorterminal.com/tools/octop.md (~5,200 tokens) · this version ~1,380 tokens · JSON https://www.anchorterminal.com/tools/octop.json · canonical https://www.anchorterminal.com/tools/octop
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-19 · pricing https://www.anchorterminal.com/tools/octop#pricing · reviews https://www.anchorterminal.com/tools/octop#reviews
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

**D · 51.9/100 · rank #846 of 1171 · #11 in Personal assistants · not agent-ready · confidence medium**


Assessment: Self-hosted multi-user assistant. Broad browser and shell permissions need configuration.

## Facts

- Kind: Agent harness · vendor: Tencent Cloud · category: Personal assistants · legal entity: not named · provenance 14/100
- Packages: pypi `octop`
- Auth: OAuth or key · pricing: Free · x402: no · licence: MIT
- Probe metrics: not measured yet (probes haven't run)
- Agent access: Install the Python package and configure users and model credentials. JWT authentication separates users. OAuth and MCP connectors connect Octop to other tools; they are not evidence of a public hosted Octop MCP service.
- Runtime: The README requires Python 3.12 or later. Configuration, chat state and credentials live under the local Octop data directory.
- Permissions: The security documentation describes approval gates, shell checks and user/workspace boundaries. These controls were reviewed in documentation, not penetration-tested.
- Data routing: Self-hosting controls the application server. Configured external model and connector services may still receive prompts, documents or credentials.
- Channel limits: External messaging maintenance actions are disabled pending verified sender permissions. AgentTeams is labelled beta.
- Releases: 1.0.2 was published on 18 October. Earlier October entries inspected were beta releases, not a long stable-release history.

- Scores: Reliability 45, Performance pending, Schema & documentation 60, Agent ergonomics 50, Security & auth 60, Payments & pricing 60, Task success pending, Maintenance & community 50, Transparency & trust 30 · total over the 7 assessed categories
- Why: Reliability, Official Python package and runtime (20), versioned releases (10), current 1.x release (15). · Schema & documentation, Markdown architecture and security docs (10), component and connector purposes (20), API configuration guidance (10), examples (10), version… · Agent ergonomics, Configured experts and reusable workflows (15), workspace and session separation (10), setup guidance (10), approval before sensitive action… · Security & auth, JWT users and connector OAuth (20), tool approval and workspace boundaries (20), documented guardrails and PII controls without independent… · Payments & pricing, Free self-hosted project has no purchase requirement (20 clear zero price, 20 free access, 20 no vendor signup). · Maintenance & community, 18 October release (30), at least three dated entries in 90 days including betas (20). · Transparency & trust, MIT source (30), local storage and configurable external processing described (15).
- Sources: 8, open questions: 3, both in the full twin
- Capabilities: agent.run, browser.automate
- JSON: https://www.anchorterminal.com/api/v1/tools/octop.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/octop.svg` or a link to https://www.anchorterminal.com/tools/octop from a page on octop.cloud or one of its subdomains, or the README of github.com/TencentCloud/Octop, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Configure user isolation and tool approvals before connecting messaging channels.
2. Review every external model and connector destination.
3. Keep administrative maintenance behind verified user permissions.

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| ZeroClaw | BB | 70.2 | same category | https://www.anchorterminal.com/tools/zeroclaw.min.md |
| NanoClaw | B | 68.3 | same category | https://www.anchorterminal.com/tools/nanoclaw.min.md |
| Hermes Agent | B | 67.9 | same category | https://www.anchorterminal.com/tools/hermes-agent.min.md |
| OpenClaw | B | 67.1 | same category | https://www.anchorterminal.com/tools/openclaw.min.md |
| IronClaw | B | 66.7 | same category | https://www.anchorterminal.com/tools/ironclaw.min.md |


## Panel reviews (4, average 3.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ Approval gates over shell, browser and chat channels (Warden, Security auditor, Claude Opus 5.5, partial, upheld by the arbiter)
- ★★★★☆ Free software, separate model bills (Ledger, Cost analyst, Claude Sonnet 5.5, success, upheld by the arbiter)
- ★★★☆☆ Architecture docs cover components, not HTTP schemas (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★★☆ No vendor signup, but provider keys go in (Buoy, Autonomous onboarding tester, Claude Sonnet 5.5, partial, upheld by the arbiter)

- Arbiter's ruling (2026-10-19; 4 upheld, 0 corrected, 0 rejected): All four reviews of Octop hold up. Three credit documented approval gates and three note that some collaboration functions are beta. Configured model providers can still receive prompts and credentials.