Rating certificate · AW/26-09/48826 Sept 2026
75of 100
The Register / Coding agents / OpenCode
Register entry · Coding agents · updated 26 Sept 2026
OpenCode
OpenCode is an MIT-licensed coding agent that runs in the terminal, as a desktop app or via an IDE extension, and connects to many model providers or local models. Anomaly also sells optional model access: OpenCode Zen (pay-as-you-go curated models) and OpenCode Go ($10/month subscription to open-weight coding models). Most tool permissions default to allow; access outside the project directory defaults to ask.
What reviewers and users praise
- Model freedom: one config change to switch provider or run locally (Composio, heyuan110)
- Low-cost access through the $10 Go plan (Thomas Wiegold; multiple HN users)
- Works reasonably well across many models out of the box (HN)
What they criticise
- Fast release cadence brings regressions (AICoderScope)
- High memory/CPU use reported (GitHub Memory Megathread; HN)
- Repeated serious security advisories in 2026, including unauthenticated command execution
- Security track record judged weaker than Claude Code (heyuan110)
Experts vs the crowdcrowd cooler by 17
Experts71
Crowd53
| Price | Free, paid from $10 |
|---|---|
| Use it via | CLI, Desktop app, IDE extension, Web app |
| Runs on | macos, linux, windows |
| Licence | MIT |
| Updated | Evidence collected 26 Sept 2026 |
How the rating was worked out
Weights for Coding agents: adoption 35%, experts 40%, crowd 25%. Pillars without enough evidence are left out and the others re-weighted. The method.
| Adoption & momentumweight 35% | 95 | GitHub stars 210k → 100 · npm weekly downloads 2.2M → 90 · Reported users 16M → 87 · 42 releases in 90 days → 100reach × 0.7 + momentum × 0.3 |
|---|---|---|
| Expertsindependent reviews · weight 40% | 71 | 9 independent reviews (5 positive · 4 mixed · 0 negative), averaged toward 50 for small samples. Benchmarks, shown not scored: Terminal-Bench 2.0 No. 36 of 43 (OpenCode + Claude Opus 4.5) |
| Crowdcommunity sample · weight 25% | 53 | 23 dated posts from hackernews, forum: 11 positive · 3 mixed · 9 negative (positive + ½ mixed) ÷ n, averaged toward 50 for small samples |
| Rating | 75 | high confidence (3 of 3 pillars, 23 community posts). |
Evidence checks. 1 GitHub issue not counted as sentiment. 1 item could not be checked at the source (the page could not be fetched, or the quote is from a comment under the linked post); kept and marked “unverified”. How evidence is checked.
Editorial adjustment. Incident-history re-grade under methodology revision 2 (see the trust section).
Trust & safety
Seven dimensions graded A–D from documented facts. Overall: B.
C
Permission model
Docs: most permissions default to "allow"; only doom_loop and external_directory default to "ask". No sandbox; allow/ask/deny configurable per tool. source
A
Data access scope
Access outside the project directory is gated by the external_directory permission (default ask) with path-pattern allowlists. source
A
Data storage
Runs locally; enterprise docs state OpenCode does not store code or context data. Optional /share uploads conversations to opencode.ai. source
n/e
Data retention & training
Depends on provider. Zen docs: most Zen providers zero-retention/no training; OpenAI and Anthropic requests retained 30 days; some free models may use data for improvement. Mixed, so not graded. source
C
Incident history (24 months)
Three GitHub security advisories in 2026 (two high, one critical), all with patched versions. Regraded from D: Revision 2: serious issues that were each fixed and publicly disclosed grade C; D is kept for unresolved issues or slow or undisclosed fixes. source
D
Compliance
No SOC 2 / ISO 27001 attestation found in enterprise docs. source
A
Transparency
MIT licence, public GitHub releases. source
The experts
9 named independent reviews found; dated reviews from the last 12 months are scored.
- positive
Pick OpenCode if you want a low-cost alternative that lets you use any and all models.
Prathit Joshi (Composio blog) · 11 Jun 2026 · composio.dev - positive
OpenCode is the most serious open-source terminal coding agent available right now.
AICoderScope · 29 May 2026 · aicoderscope.com - mixed
Security is a top priority (Claude Code’s track record is cleaner)
heyuan110.com · 13 Mar 2026 · heyuan110.com - positive
OpenCode Go is the cheapest multi-model AI coding subscription available in 2026.
Thomas Wiegold · 15 Apr 2026 · thomas-wiegold.com - mixed
OpenCode has closed the feature gap considerably. For everyday tasks — multi-file edits, shell commands, codebase search, refactors — it's hard to tell the difference from Claude Code.
Jason Zhou (AI Builder Club) · 28 May 2026 · aibuilderclub.com - positive
Why OpenCode Beat Out Every Other AI Coding Harness I Tried
Hamza Boulahia (Towards AI) · 6 Aug 2026 · unverified · pub.towardsai.net - positive
OpenCode constructs an argument that I find difficult to refute: the terminal is not a compromise.
Murat Akdeniz (Codexpedite) · 20 May 2026 · codexpedite.com - mixed
OpenCode is a brilliant executor, but a terrible architect.
RuView Blog · 19 Jun 2026 · ruview.pro - mixed
While OpenCode + Oh-My-OpenCode has impressive performance, there's a lot of dead time where nothing is happening.
Chandler (chand1012, DEV Community) · 23 Jan 2026 · dev.to
The crowd
23 coded posts from hackernews, forum.
11 positive3 mixed9 negative
- positive
enjoying my $10 OpenCode Go sub, dual OEM spark setup, and open weights.
Hacker News comment · 25 Sept 2026 · news.ycombinator.com - negative
I may end this and go back to my own, opencode is so sloppy, but then what harness isn't?
Hacker News comment · 23 Sept 2026 · news.ycombinator.com - positive
opencode, pretty good setup out of the box, no need to go through and find packages for the basics like pi
Hacker News comment · 23 Sept 2026 · news.ycombinator.com - negative
I do not know why but opencode pushes CPU usage to very high which has NOT happened with DeepSeek harness even once.
Hacker News comment · 22 Sept 2026 · news.ycombinator.com - positive
OpenCode works pretty well for all models
Hacker News comment · 23 Sept 2026 · news.ycombinator.com - negative
session management - accurate (unlike OpenCode last time I tried)
Hacker News comment · 23 Sept 2026 · news.ycombinator.com - mixed
Love Pi because it does a good job managing the context, open code meh, claude code nope.
Hacker News comment · 23 Sept 2026 · news.ycombinator.com - negative
your system will probably be pwned soon since it's JS + NPM + vibe coding
Hacker News comment · 24 Apr 2026 · news.ycombinator.com
Pricing
As published, checked 26 Sept 2026.
| Plan | Price | Notes |
|---|---|---|
| Free (BYOK) | Free | MIT-licensed agent; pay your own model provider. Some free models offered via Zen. |
| OpenCode Go | $10 / monthly | Subscription to 30+ open-weight coding models with usage limits per 5-hour window. |
| OpenCode Zen | Custom | Pay-as-you-go per 1M tokens; card fees passed at cost (4.4% + $0.30). |
| Enterprise | Custom | Per-seat; contact sales. |
Recent changes
Ranked alongside
Other ranked entries in Coding agents.
Claude CodeAnthropic73
Zed (Agent Panel)Zed Industries73
GitHub CopilotGitHub (Microsoft)72
Codex (CLI and app)OpenAI71
Grok BuildSpaceXAI (formerly xAI)68
Sources
Every figure above traces to one of these, observed up to 26 Sept 2026.