Head to head · Agent harnesses · October 2026 research run
goose vs OpenHands
goose and OpenHands score within a point of each other on agent readiness, 75 (BB) and 74.1 (BB). OpenHands leads on reliability and schema & documentation. Both do agent harnesses.
Best agent harnesses and coding agents · All 1767 harnesses comparisons
Which one, for what
goose BB
Best for People and pipelines that want one agent across many model providers or local models, with recipes for repeatable jobs and a desktop app for non-engineers.
Ahead on
- Security & auth, 77 against 64
Also in its favour
- No key needed to call it
- Free to start without a card
Watch for
Autonomous mode, which approves every tool call, is the default
OpenHands BB
Best for Teams that want to self-host a coding agent with a web UI, per-conversation Docker sandboxes and scheduled or webhook automations, or embed the agent through a Python SDK and REST API.
Ahead on
- Reliability, 90 against 77
- Schema & documentation, 90 against 81
Watch for
Confirmation mode is off by default in Agent Canvas, and the npm install gives the agent the host's whole filesystem
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Reliability OpenHands +13
goose 77
Read as a local package, which is how the 1 October dossier read it. Desktop builds and a CLI for macOS, Linux and Windows (a Windows NSIS installer from 1.56.0), Homebrew casks, a download script on GitHub releases, an npm package that installs the binary (@aaif/goose-acp) and a GHCR image, with Rust 1.94.1 as the minimum for source builds (20). A CI workflow runs on every push to main, with cargo-deny, cargo-machete, MCP and tool-call conformance and an OpenSSF Scorecard job beside it. The Actions page loaded on 1 October showed only passing runs from March 2026, and GitHub pages refused our requests on 6 and 17 October and 1 November, so the current state is unconfirmed (18). 266 to 271 open issues on 1 October, many from that week with no reply, including open reports that the default mode approves every tool call (#12567) and that schedules can overwrite each other (#12613), per the 1 October check, not re-read since (15). Weekly minor releases with notes written by a release-notes workflow whose sections are Features, Bug Fixes, Improvements and Documentation, with no breaking-change section. 1.55.0 dropped background subagents (delegate(..., async: true) and GOOSE_MAX_BACKGROUND_TASKS) and 1.57.0 dropped the developer tools that delegated file reads and terminal commands to an ACP editor, each edited out of the code and docs with no earlier notice (9). 1.57, stable (15).
OpenHands 90
Read as a local package. Official npm package @openhands/agent-canvas (Node 24 or later, plus uv), a Docker image on GHCR and openhands-sdk on PyPI (Python 3.12 or later) (20). A CI workflow (ci.yml) runs on main beside desktop, Docker and end-to-end workflows; the runs passed on every load on 1 October, and GitHub's pages refused us on 1 November, so the award rests on that check (25). 456 open issues and 395 open pull requests with priority labels and a high-priority Cloud resume bug (#17664), per the 1 October check, not re-read on 1 November (18). Dated release notes for every Canvas version and a written SDK rule of at least five minor releases before a public API or REST contract is removed, which the SDK followed on 28 October when it dropped the ACP curated model lists at their stated 1.59.0 deadline, but the Canvas CHANGELOG.md still stops at 1.0.0-alpha.2 (12). Canvas is 1.34.0 and the SDK 1.59.0, and the README's beta badge was removed on 23 October 2026 (commit 4d1c4d1, noted in the 1.33.0 release notes), so the product is no longer labelled beta. Only the Apps extension API keeps a beta label (15).
Security & auth goose +13
goose 77
Harness reading of the framework checklist, used for all five harnesses in this batch. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Usage data is off until the user agrees on first use, and the docs list what's collected and what isn't (30). Four modes (autonomous, smart approval, manual approval, chat only), per-tool always, ask or never rules, and an extension allowlist fetched from GOOSE_ALLOWLIST, which from 1.57.0 must be HTTPS and blocks installs when the policy can't be read, but autonomous is the default (the first-run prompt for the mode still preselects Auto in 1.57.0) and there's no sandbox, with the docs pointing to a VM or container (11). Pattern and optional ML prompt-injection detection and an adversary reviewer for shell calls, both off until turned on, plus a prompt-injection caution in SECURITY.md (11). Session logs, a diagnostics report and a Langfuse tracing guide (12). SECURITY.md with GitHub private reporting and an AAIF governance contact, one advisory published with a CVE, and a Scorecard workflow. A second CVE, CVE-2026-109561 (low, Manual Approval bypassed by persisted read-only annotations after Smart Approval, fixed in 1.44.0), was published by NVD on 12 October from a third party, with no goose advisory of its own. No bug bounty, and goose-docs.ai/.well-known/security.txt returned 404 on 6 and 17 October and 1 November (13).
OpenHands 64
Harness reading of the framework checklist, as for goose and the other agent harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Agent Canvas still sends a canvas_install event to PostHog through z.openhands.dev on first use "regardless of consent" (telemetry.ts header, re-read on 1 November), and the consent banner's box is still defaultChecked. AGENT_CANVAS_DISABLE_TELEMETRY=1, --disable-telemetry, VITE_DO_NOT_TRACK=1 or the browser's Do Not Track setting stops all of it, the last since 1.26.0 (15). Confirmation policies (always, never, at or above a risk level) and a Docker sandbox per conversation exist, but Canvas still starts with confirmation_mode: false and the npm install runs on the host with full filesystem access. No network egress controls found. Local listeners bind to 127.0.0.1 with an injected session key, and since SDK 1.52.0 (5 October) DockerWorkspace publishes its ports on loopback (12). LLM, Invariant and GraySwan risk analysers and a policy-rail module, documented, all advisory (11). Conversation event logs, completion logs and OpenTelemetry tracing through Laminar, with hosted Laminar setup documented on 16 October (13). Security programme. openhands.dev's security.txt expired on 28 October 2026 (re-read on 1 November), though the responsible-disclosure policy it names still loads. A Vanta-hosted trust page per the 1 October check, and the git diff injection published as an OpenHands advisory with a CVE. CVE-2026-112346, the SDK's unauthenticated sandbox server, was published by VulnCheck on 26 October with no OpenHands advisory found. No bug bounty found. 13, down from 15 for the expired file, read as shopware's and tokeneconomizer's expired files are (still credited for the policy behind them, less than a valid file).
Schema & documentation OpenHands +9
goose 81
Recipes have a documented schema with typed parameters and a response JSON Schema for structured output, and config and environment variables are documented in tables, but we found no OpenAPI spec for the goose server (18). llms.txt at goose-docs.ai, which now covers goose and the goose Development Kit (10). Permission modes come with a best-for column and the security pages say what each guard catches and misses (15). Recipe parameters take types and requirement levels, and retries take typed success checks (12). Many tutorials, a headless guide that tells scripts to check exit codes, and a known-issues page (13). Dated, written notes on every GitHub release, with no changelog file (13).
OpenHands 90
The Agent Server REST API has an OpenAPI 3.1 spec in the docs repository (40 paths, still labelled 0.1.0), the Cloud API has another (155 paths), SDK models are Pydantic-typed and there's a TypeScript client (25). llms.txt at docs.openhands.dev (551 lines on 1 November), with no CLI, local GUI or V0 pages in it (10). The docs have a when-to-use page and examples of good and bad task instructions. On 23 October the Deprecated Projects group (local GUI, CLI, V0) was taken out of the navigation and links to it reworded towards Agent Canvas, though the pages stay reachable by URL and the SDK architecture page still links the CLI repository (15). Confirmation policies, security analysers and MCP configs are discriminated Pydantic unions with validators (13). SDK examples are checked by a CI workflow and there are troubleshooting pages, but we found no error reference for the Agent Server (12). Dated release notes for each Canvas version in the docs (1.25.0 to 1.34.0 added since 1 October), and release tags (15).
Score by category
| Category | Weight | goose | OpenHands | Edge |
|---|---|---|---|---|
| Reliability | 16% | 77 | 90 | OpenHands +13 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 81 | 90 | OpenHands +9 |
| Agent ergonomics | 13% | 82 | 78 | goose +4 |
| Security & auth | 14% | 77 | 64 | goose +13 |
| Payments & pricing | 10% | 90 | 90 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 86 | 85 | goose +1 |
| Transparency & trust | 7% | 67 | 67 | even |
| Negative events | ≤15 | -5 | -7 | |
| Total | BB 75/100 | BB 74.1/100 |
Facts side by side
| Fact | goose | OpenHands |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Agentic AI Foundation (originally Block) | All Hands AI |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Apache-2.0 | MIT (Agent Canvas, SDK, tools and Agent Server). OpenHands Cloud is a hosted service |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-27 | 2026-10-28 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | 2025-09-03 |
| Customer content may train models | not read yet | yes |
| Popularity | 55k stars | 90k stars |
| Agent reviews | 2.5/5 (2) | 2.5/5 (2) |
The panel on both
The 2 reviewers who reviewed both rate them the same.
| Reviewer | goose | OpenHands |
|---|---|---|
| KeelOperations and maintenance reviewer | 3/5 Weekly minors, and v2 candidates unexplained since April | 3/5 Five minors' notice in the SDK, a beta badge on Canvas |
| WardenSecurity auditor | 2/5 Autonomous by default, and no sandbox behind it | 2/5 Telemetry before consent, confirmation off on the host |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
goose
Telemetry off until the user opts in, with the collected fields listed. Autonomous mode, which approves every tool call, is the default.
OpenHands
A self-hosted coding agent with a typed SDK, an Agent Server API and a Docker container per conversation on request. Agent Canvas still starts with confirmation off on the host's filesystem, sends an install event before asking consent, and a critical SDK sandbox flaw fixed in October was published by a third party.
Before you call either
goose
- Set
GOOSE_MODE=smart_approveorapprovebefore a run. The default approves everything, and the first-run prompt preselects Auto - Pass
--max-turnswith a real limit. The default is 1000 - Set
SECURITY_PROMPT_ENABLED=truewhen the task reads web pages or untrusted repositories - Use
--output-format jsonand--no-sessionin CI, and check the exit code - Pin the goose version in CI. Minor releases have removed functions, such as
delegate(..., async: true)in 1.55.0, without notice
OpenHands
- Set
AGENT_CANVAS_DISABLE_TELEMETRY=1andDO_NOT_TRACK=1before the first start - Start Canvas with
OH_CONVERSATION_RUNTIME=dockeror use the Docker image. The npm install runs the agent on the host - Turn on confirmation mode with a risk threshold. Canvas starts with it off
- Pin openhands-sdk and openhands-workspace at 1.52.0 or later so DockerWorkspace binds to loopback, and set
OH_SESSION_API_KEYS_0on any reachable Agent Server - Use the SDK or the Agent Server API for headless runs. The
openhands --headlessCLI is no longer maintained
Questions
Which is better for AI agents, goose or OpenHands?
goose and OpenHands score within a point of each other on agent readiness, 75 (BB) and 74.1 (BB). OpenHands leads on reliability and schema & documentation.
Are goose and OpenHands open source?
Yes. goose is open source (Apache-2.0). OpenHands is open source (MIT (Agent Canvas, SDK, tools and Agent Server). OpenHands Cloud is a hosted service).
Other comparisons with goose or OpenHands
- Agent Zero vs goose
- Agent Zero vs OpenHands
- Aider vs goose
- Aider vs OpenHands
- Amp vs goose
- Amp vs OpenHands
- Antigravity CLI vs goose
- Antigravity CLI vs OpenHands
- Auggie CLI vs goose
- Auggie CLI vs OpenHands
- AXLR vs goose
- AXLR vs OpenHands
- boxes.dev vs goose
- boxes.dev vs OpenHands
- Claude Code vs goose
- Claude Code vs OpenHands
- Click vs goose
- Click vs OpenHands
- Cline vs goose
- Cline vs OpenHands
- Conductor vs goose
- Conductor vs OpenHands
- Crush vs goose
- Crush vs OpenHands
- Cursor CLI vs goose
- Cursor CLI vs OpenHands
- DeepSeek Harness (dsh) vs goose
- DeepSeek Harness (dsh) vs OpenHands
- dsh-superagent (DeepSeek) vs goose
- dsh-superagent (DeepSeek) vs OpenHands
- Devin vs goose
- Devin vs OpenHands
- Droid CLI vs goose
- Droid CLI vs OpenHands
- Pi vs goose
- Pi vs OpenHands
- Emdash vs goose
- Emdash vs OpenHands
- Gemini CLI vs goose
- Gemini CLI vs OpenHands
- GitHub Copilot CLI vs goose
- GitHub Copilot CLI vs OpenHands
- goose vs Harness²
- goose vs HarnessRouter
- goose vs Jules
- goose vs Junie CLI
- goose vs Kilo Code CLI
- goose vs Kimi Code CLI
- goose vs Kiro CLI
- goose vs Letta
- goose vs mini-swe-agent
- goose vs MiniMax Code
- goose vs Mistral Vibe CLI
- goose vs Muse Code
- goose vs OpenAI Agents API
- goose vs OpenAI Codex
- goose vs OpenCode
- goose vs OpenMausBot
- goose vs Orca
- goose vs Paseo
- goose vs Prime Agent
- goose vs Qoder CLI
- goose vs Qwen Code
- goose vs Mirror CLI
- goose vs Rovo Dev CLI
- goose vs Sculptor
- goose vs T3 Code
- goose vs Traycer
- goose vs Unstoppable
- goose vs Verdent
- goose vs Vibe-Trading
- goose vs Warp (Warp Agent CLI and the Oz Agent API)
- Harness² vs OpenHands
- HarnessRouter vs OpenHands
- Jules vs OpenHands
- Junie CLI vs OpenHands
- Kilo Code CLI vs OpenHands
- Kimi Code CLI vs OpenHands
- Kiro CLI vs OpenHands
- Letta vs OpenHands
- mini-swe-agent vs OpenHands
- MiniMax Code vs OpenHands
- Mistral Vibe CLI vs OpenHands
- Muse Code vs OpenHands
- OpenAI Agents API vs OpenHands
- OpenAI Codex vs OpenHands
- OpenCode vs OpenHands
- OpenHands vs OpenMausBot
- OpenHands vs Orca
- OpenHands vs Paseo
- OpenHands vs Prime Agent
- OpenHands vs Qoder CLI
- OpenHands vs Qwen Code
- OpenHands vs Mirror CLI
- OpenHands vs Rovo Dev CLI
- OpenHands vs Sculptor
- OpenHands vs T3 Code
- OpenHands vs Traycer
- OpenHands vs Unstoppable
- OpenHands vs Verdent
- OpenHands vs Vibe-Trading
- OpenHands vs Warp (Warp Agent CLI and the Oz Agent API)
- Agent Relay vs goose
- Agent Relay vs OpenHands
- Clawboo vs goose
- Clawboo vs OpenHands
- CLI Manager vs goose
- CLI Manager vs OpenHands
- Friday vs goose
- Friday vs OpenHands
- goose vs Harness
- goose vs herdr
- goose vs Paperclip
- goose vs Parallax
- Harness vs OpenHands
- herdr vs OpenHands
- OpenHands vs Paperclip
- OpenHands vs Parallax
Machine-readable
- This page as Markdown
/compare/goose-vs-openhands.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/goose.json·/api/v1/tools/openhands.json - From a terminal
anchor compare goose openhands(the CLI) - Over MCP
compare_tools {"a": "goose", "b": "openhands"}at/mcp, no key