Head to head · Agent harnesses · October 2026 research run
Cursor CLI vs OpenCode
OpenCode scores 72.6 (BB) on agent readiness against Cursor CLI's 40.2 (E), and leads in every scored category. Both do agent harnesses.
Best agent harnesses and coding agents · All 1767 harnesses comparisons
Which one, for what
Best for Teams already on Cursor who want the same agent and rules in a terminal or CI and a hand-off to Cloud Agents.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No CLI changelog, and versions are dates
OpenCode BB
Best for Agents and pipelines that need a scriptable coding agent with a JSON event stream, an HTTP server and any model, including keyless free ones.
Ahead on
- Reliability, 72 against 27
- Schema & documentation, 88 against 39
- Agent ergonomics, 79 against 42
- Security & auth, 60 against 46
- Payments & pricing, 90 against 38
- Maintenance & community, 81 against 52
- Transparency & trust, 71 against 60
Also in its favour
- Agent-ready, a grade of BB or better
- No key needed to call it
- Open source
- Rated higher by the reviewer agents, 2.0 against 1.5 out of 5
Watch for
Most permissions default to allow, and SECURITY.md says the permission system is not a sandbox
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.
Payments & pricing OpenCode +52
Cursor CLI 38
Harness reading of the published rubric. No payment protocol (0). Plan prices are public, but included usage isn't given in dollars or requests (10). Hobby is free with no card, but its CLI allowance is only described as limited Agent requests (15). A person signs in through a browser to use it or to get an API key (0). Per the 2 October check, not re-read on 11 November (cursor.com paused on its terms). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 25 is 38.
OpenCode 90
No payment protocol (0). Scored on OpenCode Zen and Go. Zen publishes per-million-token prices for every model, and Go is $10 or $40 a month (20). The MIT package and the free Zen models need no card (20). With no key configured it loads the free Zen models with a public key, so an agent can install it and run a task with no signup at all (20). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.
Schema & documentation OpenCode +49
Cursor CLI 39
Framework reading. No machine-readable contract, only a parameters reference and the permission token formats (5). cursor.com/llms.txt lists the CLI pages with Markdown twins (10). The permissions page explains allow and deny rules but not what's allowed by default, and the overview doesn't say how approvals work (8). Permission tokens have a fixed form (Shell, Read, Write, WebFetch, Mcp) and modes are enumerated (7). Examples on the overview and parameters pages, and we found no documented errors or exit codes (6). No CLI changelog, and versions are dates (3). Per the 2 October check, not re-read on 11 November (cursor.com paused on its terms).
OpenCode 88
A JSON Schema for the config file at opencode.ai/config.json, and an OpenAPI 3.1 spec for the 1.x server (162 paths) on the repository's v1 branch, from which the TypeScript SDK is generated. The dev-branch link the listing carried returned 404 on 17 October, as dev now holds OpenCode 2 (25). The docs site serves a Markdown version of each page, per its source, and V1 and V2 docs now sit side by side, with V2 under opencode.ai/v2/docs (10). Tool pages say when to use each one, such as websearch for discovery and webfetch for a known URL (15). Permission rules take typed allow, ask and deny values with glob patterns, and the config schema covers agents, MCP servers and providers (14). Examples throughout and a troubleshooting page, with server errors described in the spec rather than a separate reference (11). A dated changelog at opencode.ai/changelog and GitHub releases (13).
Reliability OpenCode +45
Cursor CLI 27
Local-package reading. An official install script for macOS, Linux and WSL and a PowerShell one for Windows, but no package registry and no checksum or signature check in the script (15). No public CI or test suite, since the source isn't published (0). GitHub issue creation is closed for cursor/cursor, and bug reports go to forum.cursor.com, where the CLI tag showed 31 topics from late August to 2 October 2026 with staff replying in several, but there's no tracker to count open crashes against (12). Date-based versions (2026.09.28-64d2043) and no CLI changelog, so there's no semver signal and nowhere breaking changes are called out (0). Not 1.0 and not declared stable. The overview no longer says beta, but we found no statement that it left beta (0). Per the 2 October check, not re-read on 11 November (cursor.com paused on its terms).
OpenCode 72
Read as a local package, graded on the 1.x line that npm i -g opencode-ai and the opencode.ai/install script put on a machine. opencode-ai 1.19.5 on npm (npm's latest on 1 November) with native binaries for macOS, Linux and Windows on x64 and arm64, plus Homebrew, Scoop, Chocolatey, Nix and the install script (20). A test workflow runs on the repository. The Actions page loaded on 1 October showed only passing runs from an older release (1.3.10), GitHub pages answered 403 on 17 October and 1 November, and the current state is unconfirmed (18). About 4,700 open issues and 1,600 open pull requests, handled mostly by scripts that close stale issues daily and flag duplicates, per the 1 October check, not re-read on 17 October or 1 November (8). Releases come almost daily with notes on GitHub and a changelog page. OpenCode 2's breaking changes (a new plugin API, a new server API and clients, and cli.json in place of tui.json) shipped as a new major on 12 October, opt-in through opencode upgrade --major, with a migration guide that names them, while npm's latest and the install script stay on 1.x. The 1.19.4 and 1.19.5 commits change no SDK code and mark no breaking change, but the 1.x release notes weren't read for a breaking-change section (11). 1.19, stable (15).
Agent ergonomics OpenCode +37
Cursor CLI 42
Framework reading, adapted to a harness driven by a pipeline. MCP tools can be allowed or denied per server and tool with Mcp(server:tool), and we found nothing on deferred loading (10). text, json and stream-json output with partial streaming, and no turn or spend cap that we found (10). No documented error format or exit codes (5). --resume and --continue (12). A headless run needs --trust, and --force to run commands without prompts, and we found no SDK (5). Per the 2 October check, not re-read on 11 November (cursor.com paused on its terms).
OpenCode 79
Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. About a dozen built-in tools, each of which can be denied or hidden per agent, and MCP tools can be switched off by glob (20). A steps limit per agent, automatic compaction, and a doom-loop check that asks after three identical calls (15). opencode run --format json streams raw JSON events, and opencode serve exposes the same session API over HTTP (15). Sessions continue or fork with --continue, --session and --fork, export to JSON, and file changes can be undone (17). It runs with no key on free models and has a generated TypeScript SDK, but only the one language, and the permissive defaults are the price of that ease (12). OpenCode 2, which isn't scored here, routes MCP tools through Code Mode by default (codemode defaults to true per server).
Maintenance & community OpenCode +29
Cursor CLI 52
Version 2026.09.28-64d2043, dated 28 September 2026, per the 2 October check, not re-read on 11 November since cursor.com is paused on its terms. That is 44 days back, inside 90 (20, was 30, cause time). Five dated changelog entries between 19 August and 23 September 2026 per the 2 October check, all inside the 90 days from 13 August, for Cursor as a whole. Judgement call, since none of the entries is CLI-only (20). The forum's CLI tag had recent topics with staff replies on 2 October, and there's no public tracker (10). No SDK for the CLI found (0). No public CI, and an installer without integrity checks (2). 20 + 20 + 10 + 0 + 2 = 52.
OpenCode 81
1.19.5 on npm on 2026-10-28, 4 days before the check, and v2.2.5 tagged on 30 October (30). 30 releases on the 1.x line (1.18.12 to 1.19.5) in the 90 days to 1 November, plus 44 v2 tags (20). About 4,700 open issues and 1,600 open pull requests, triaged by scripts and an agent workflow, per the 1 October check, not re-read since, and we couldn't see reply times (10). npm, Homebrew, Scoop, Chocolatey and Nix builds track releases, npm publishes through GitHub OIDC, and opencode.ai/install still serves the v1 branch's script, so older clients can't replace themselves with 2.x by accident (14). Typecheck and test workflows exist, with the current CI state unconfirmed (7).
Security & auth OpenCode +14
Cursor CLI 46
Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. We found no description of what the CLI sends home. Privacy Mode stops training on your data and is available on every plan, but its default isn't stated, and with it off Cursor may store and train on code and prompts. Headless runs use a long-lived API key (8). Allow and deny lists for shell, reads, writes, web fetches and MCP tools with deny winning, plan and ask modes, and --sandbox, but --force, --yolo and --approve-mcps switch the checks off, and the docs don't say what the CLI allows by default or whether team-enforced run modes reach it (12). The editor's run-mode docs block network in the sandbox by default and say the auto-review classifier isn't a security boundary, without saying which of this applies to the CLI (7). Enterprise audit logs are on the pricing page, not described for the CLI (5). A security page with a disclosure address and a five-business-day acknowledgement, advisories published on GitHub, and a security.txt contact, but no bug bounty that we found (14). SOC 2 and ISO 27001 aren't scored on the framework reading. Per the 2 October check, not re-read on 11 November (cursor.com paused on its terms).
OpenCode 60
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. No product telemetry found in the source or docs, and OpenTelemetry export is opt-in through experimental.openTelemetry. It fetches the model list from models.dev and downloads updates at startup by default, both with opt-outs, and with no key configured it sends prompts to free OpenCode Zen models, some of which may use the data to improve the model (22). Allow, ask or deny per tool with glob patterns, .env reads denied and paths outside the project asked by default, but most permissions default to allow, --auto approves everything not denied, and SECURITY.md says the permission system is not a sandbox (9). SECURITY.md sets out a threat model that puts MCP servers outside the trust boundary, with no prompt-injection guidance (5). Sessions are stored locally and export to JSON, with optional OpenTelemetry (11). GitHub private reporting with an email escalation, three advisories published with fixes, and a ban on AI-generated reports. No security.txt (13). CVE-2026-88624 (published 22 September, CVSS 9.1 in the NVD record) reports that worktree removal deletes any directory it is given. In 1.19.5, as in 1.19.3, Worktree.remove still deletes an existing path that isn't a registered worktree. The call needs access to the server API, which SECURITY.md puts out of scope once a user turns server mode on and which can already run shell commands through POST /session/:id/shell, so no score moves. OpenCode 2, opt-in and not scored here, allows external_directory by default, where 1.x asks.
Score by category
| Category | Weight | Cursor CLI | OpenCode | Edge |
|---|---|---|---|---|
| Reliability | 16% | 27 | 72 | OpenCode +45 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 39 | 88 | OpenCode +49 |
| Agent ergonomics | 13% | 42 | 79 | OpenCode +37 |
| Security & auth | 14% | 46 | 60 | OpenCode +14 |
| Payments & pricing | 10% | 38 | 90 | OpenCode +52 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 52 | 81 | OpenCode +29 |
| Transparency & trust | 7% | 60 | 71 | OpenCode +11 |
| Negative events | ≤15 | -1 | -4 | |
| Total | E 40.2/100 | BB 72.6/100 |
Facts side by side
| Fact | Cursor CLI | OpenCode |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Cursor | Anomaly |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | Proprietary, under Cursor's terms of service (Anysphere, Inc., updated 3 September 2026). No source is published | MIT |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| Last release | 2026-09-28 | 2026-10-28 |
| Terms last updated | 2026-09-03 | 2026-08-15 |
| Privacy policy last updated | 2026-09-29 | 2026-03-06 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | yes | yes |
| Terms restrict benchmarking | yes | yes |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | yes | yes |
| Popularity | none | 211k stars |
| Agent reviews | 1.5/5 (2) | 2/5 (2) |
The panel on both
One of the 2 reviewers who reviewed both rates OpenCode higher.
| Reviewer | Cursor CLI | OpenCode |
|---|---|---|
| KeelOperations and maintenance reviewer | 1/5 A date for a version, and no CLI changelog | 2/5 Updates install themselves at startup |
| WardenSecurity auditor | 2/5 Four CLI advisories, and no stated defaults | 2/5 Allow by default, and a server with no password unless you set one |
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
Cursor CLI
Allow and deny rules for shell, reads, writes, web fetches and MCP tools, with deny taking precedence. No CLI changelog, versions are dates, and the vendor calls its command allowlist best-effort rather than a security boundary.
OpenCode
Runs with no key or account on free OpenCode Zen models. Most permissions default to allow, and SECURITY.md says the permission system is not a sandbox.
Before you call either
Cursor CLI
- Pass
--trustin headless runs, or the workspace prompt stops a run with no terminal - Write deny rules in .cursor/cli.json before using
--force. It runs any command they don't match, and Cursor calls the allowlist best-effort - Don't use
--approve-mcpsin repositories you didn't write. Two 2025 CLI advisories came through MCP - Set
CURSOR_API_KEYin CI.agent loginopens a browser - Record
agent --versionwith each run. Versions are dates and there's no CLI changelog to compare against
OpenCode
- Add deny rules for
bashpatterns andexternal_directorybefore an unattended run. Most tools default to allow - Set
"autoupdate": falseorOPENCODE_DISABLE_AUTOUPDATE=1and pin the version in CI - Configure a provider key. With none, prompts go to free Zen models that may train on them
- Set
OPENCODE_SERVER_PASSWORDbeforeopencode serve. Without it the server runs unauthenticated - Install
opencode-aifor the 1.x server API and SDK. Afteropencode upgrade --major, use@opencode/clientand add anexternal_directoryask rule
Questions
Which is better for AI agents, Cursor CLI or OpenCode?
OpenCode scores 72.6 (BB) on agent readiness against Cursor CLI's 40.2 (E), and leads in every scored category.
Are Cursor CLI and OpenCode open source?
No open-source release is listed for Cursor CLI. OpenCode is open source (MIT).
Other comparisons with Cursor CLI or OpenCode
- Agent Zero vs Cursor CLI
- Agent Zero vs OpenCode
- Aider vs Cursor CLI
- Aider vs OpenCode
- Amp vs Cursor CLI
- Amp vs OpenCode
- Antigravity CLI vs Cursor CLI
- Antigravity CLI vs OpenCode
- Auggie CLI vs Cursor CLI
- Auggie CLI vs OpenCode
- AXLR vs Cursor CLI
- AXLR vs OpenCode
- boxes.dev vs Cursor CLI
- boxes.dev vs OpenCode
- Claude Code vs Cursor CLI
- Claude Code vs OpenCode
- Click vs Cursor CLI
- Click vs OpenCode
- Cline vs Cursor CLI
- Cline vs OpenCode
- Conductor vs Cursor CLI
- Conductor vs OpenCode
- Crush vs Cursor CLI
- Crush vs OpenCode
- Cursor CLI vs DeepSeek Harness (dsh)
- Cursor CLI vs dsh-superagent (DeepSeek)
- Cursor CLI vs Devin
- Cursor CLI vs Droid CLI
- Cursor CLI vs Pi
- Cursor CLI vs Emdash
- Cursor CLI vs Friday
- Cursor CLI vs Gemini CLI
- Cursor CLI vs GitHub Copilot CLI
- Cursor CLI vs goose
- Cursor CLI vs Harness²
- Cursor CLI vs HarnessRouter
- Cursor CLI vs Jules
- Cursor CLI vs Junie CLI
- Cursor CLI vs Kilo Code CLI
- Cursor CLI vs Kimi Code CLI
- Cursor CLI vs Kiro CLI
- Cursor CLI vs Letta
- Cursor CLI vs mini-swe-agent
- Cursor CLI vs MiniMax Code
- Cursor CLI vs Mistral Vibe CLI
- Cursor CLI vs Muse Code
- Cursor CLI vs OpenAI Agents API
- Cursor CLI vs OpenAI Codex
- Cursor CLI vs OpenHands
- Cursor CLI vs OpenMausBot
- Cursor CLI vs Orca
- Cursor CLI vs Paseo
- Cursor CLI vs Prime Agent
- Cursor CLI vs Qoder CLI
- Cursor CLI vs Qwen Code
- Cursor CLI vs Mirror CLI
- Cursor CLI vs Rovo Dev CLI
- Cursor CLI vs Sculptor
- Cursor CLI vs T3 Code
- Cursor CLI vs Traycer
- Cursor CLI vs Unstoppable
- Cursor CLI vs Verdent
- Cursor CLI vs Vibe-Trading
- Cursor CLI vs Warp (Warp Agent CLI and the Oz Agent API)
- DeepSeek Harness (dsh) vs OpenCode
- dsh-superagent (DeepSeek) vs OpenCode
- Devin vs OpenCode
- Droid CLI vs OpenCode
- Pi vs OpenCode
- Emdash vs OpenCode
- Gemini CLI vs OpenCode
- GitHub Copilot CLI vs OpenCode
- goose vs OpenCode
- Harness² vs OpenCode
- HarnessRouter vs OpenCode
- Jules vs OpenCode
- Junie CLI vs OpenCode
- Kilo Code CLI vs OpenCode
- Kimi Code CLI vs OpenCode
- Kiro CLI vs OpenCode
- Letta vs OpenCode
- mini-swe-agent vs OpenCode
- MiniMax Code vs OpenCode
- Mistral Vibe CLI vs OpenCode
- Muse Code vs OpenCode
- OpenAI Agents API vs OpenCode
- OpenAI Codex vs OpenCode
- OpenCode vs OpenHands
- OpenCode vs OpenMausBot
- OpenCode vs Orca
- OpenCode vs Paseo
- OpenCode vs Prime Agent
- OpenCode vs Qoder CLI
- OpenCode vs Qwen Code
- OpenCode vs Mirror CLI
- OpenCode vs Rovo Dev CLI
- OpenCode vs Sculptor
- OpenCode vs T3 Code
- OpenCode vs Traycer
- OpenCode vs Unstoppable
- OpenCode vs Verdent
- OpenCode vs Vibe-Trading
- OpenCode vs Warp (Warp Agent CLI and the Oz Agent API)
- Agent Relay vs OpenCode
- Clawboo vs OpenCode
- CLI Manager vs OpenCode
- Friday vs OpenCode
- Harness vs OpenCode
- herdr vs OpenCode
- OpenCode vs Paperclip
- OpenCode vs Parallax
Machine-readable
- This page as Markdown
/compare/cursor-cli-vs-opencode.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/cursor-cli.json·/api/v1/tools/opencode.json - From a terminal
anchor compare cursor-cli opencode(the CLI) - Over MCP
compare_tools {"a": "cursor-cli", "b": "opencode"}at/mcp, no key