Cite

DOSSIER · Build & code · FLAGSHIP · VERIFIED 7 Sep 2026

OpenCode95FlagshipOpen-source terminal coding agent and model-agnostic harnessVerified 2026-09-07

Dossier · Build & code

OpenCode

Sixteen scored dimensions for the open-source coding agent — Go, Zen, Plan/Build, and provider privacy checked 2026-06-15.

What is OpenCode?

Decision

Open-source terminal coding agent and model-agnostic harness

Choose it when: Developers who want an inspectable open-source agent instead of a closed IDE-only copilot
Teams that need Copilot, ChatGPT, Anthropic BYOK, Zen, Go, or local models in one harness
Skip it when: You need a polished GUI IDE with Tab-as-primary workflow — Cursor may fit better
You will run Build mode on production branches without tests, Plan review, or /undo discipline
Cost: OSS agent free · BYOK any provider · OpenCode Go $10/mo (open models, generous limits) · Zen pay-as-you-go credits (from $20 top-up, auto-reload at $5 balance) · team workspaces in beta · card fees passed at cost (4.4…
Privacy: OpenCode states the agent does not store your code or context data.

Watch for Build mode can apply diffs that pass typecheck but fail course rubrics or security review

Compare with CursorHow we score

Editorial · hands-on5 sourcespricing checked 7 Sep 2026privacy checked 7 Sep 2026

What these labels mean

Editorial fit: 0–100 desk score for research-workflow fit. Not stars, not a benchmark.
Evidence level: How close the desk got: self-run, hands-on, synthesized, or vendor claim.
Dossier depth: Flagship, Solid, Lightweight, and Draft describe how finished the page is — not which tool is best.
Verification date: When pricing or privacy was last opened at the source. Not a re-score of the whole dossier.
Benchmark status: Pending means no relevant first-party test is published yet. It is not a negative score.

Open the glossary · Read the methodology

OpenCode is a tool in the VerdictPal Build & code set: Open-source AI coding agent for terminal, desktop, and IDE — 75+ model providers, Plan/Build modes, LSP support, optional OpenCode Go ($10/mo) and Zen pay-as-you-go gateway. It scores 95 out of 100 on editorial fit.

Role: Open-source terminal coding agent and model-agnostic harnessCategory: Build & codeEditorial · hands-on

OpenCode at a glance, with the date each field was checked.
Field	Value
Editorial fit	95 out of 100
Dossier status	Flagship
Set	Build & code
Role in a workflow	Open-source terminal coding agent and model-agnostic harness
Pricing	Open source Free · Go $10/mo · Zen Custom · Teams workspace Free
Training on your data	Not recorded as a plan-wide guarantee. Check the dossier's privacy notes and sources.
Last verified	2026-09-07

Editor's note

Desk hands-on 2026-06: Goated — the open-source agent we trust when the story is “show me the harness.” Plan mode first, Go for cheap open models, Zen when you need benchmarked frontier routes. Disable the free models that train on your prompts.

Public facts · vendor & repo

List prices and pay-as-you-go entry points we can cite without running our own bench. Each tile links to a source when possible.

Agent free; BYOKOpen sourceopencode.ai/docs ↗

$10/moGoopencode.ai/go ↗

Pay-as-you-go; $20 min top-upZenopencode.ai/docs/zen ↗

Beta — free tierTeams workspaceopencode.ai/docs ↗

Limits & product surface

Non-price vendor claims — multipliers, caps, and API scope. Detailed matrices live in subscription and SDK sections below.

Primary surface: local-appTool identity ↗
License: Open source agentopencode.ai ↗
Modalities: code, textTool identity ↗
Evidence tier: editorial-hands-onQuality gate ↗

How it works · agent loop

The public positioning for this product — the loop we score against on VerdictPal.

/init the repo

Generate AGENTS.md so Plan mode knows conventions before proposing diffs.

Plan then Build

Approve the plan in chat; switch to Build only when scope is bounded.

Review with /undo

Treat each Build pass as revertible; disable free models that train on prompts.

Who it fits, where it fails

Best for

Developers who want an inspectable open-source agent instead of a closed IDE-only copilot
Teams that need Copilot, ChatGPT, Anthropic BYOK, Zen, Go, or local models in one harness
Students and researchers on a budget using Go or free Zen models with spend caps
Privacy-sensitive repos where vendor storage claims matter — read Zen model exceptions first

Avoid if

You need a polished GUI IDE with Tab-as-primary workflow — Cursor may fit better
You will run Build mode on production branches without tests, Plan review, or /undo discipline
You cannot track Zen auto-reload ($20 when balance hits $5) and monthly workspace caps
You need guaranteed EU-only inference on every model without admin model allowlists

Strengths

curl / npm / brew / Docker install
Terminal TUI, desktop app beta, IDE extension
Plan mode (read-only) and Build mode (writes)
/init project analysis and AGENTS.md generation
LSP auto-load for typed context
Multi-session parallel agents
/share session links, /undo, /redo
GitHub Copilot and ChatGPT account login
75+ providers via Models.dev and /connect
OpenCode Zen pay-as-you-go gateway (BYOK compatible)
OpenCode Go subscription for open models ($10/mo)
Custom commands, themes, formatters, MCP

Weaknesses

Build mode can apply diffs that pass typecheck but fail course rubrics or security review
Zen free/promo models may retain data for training — Big Pickle, DeepSeek Flash Free, Nemotron Free, etc.
Auto-reload and monthly caps interact confusingly when balance drops below $5
Multi-session parallelism can stomp the same files without branch discipline
Desktop app is still beta — terminal remains the most documented surface
Model deprecation table moves fast — pinned configs break on schedule

Search modes · 4 lenses

One input box, many retrieval postures. Filter by tier.

01Free

Plan mode

Read-only planning before Build touches files

02Pro

Build mode

Implementation pass after approved plan

03Max

Zen routes

Pay-as-you-go benchmarked provider pairing

04Free

BYOK

Bring your own Anthropic/OpenAI/Google keys

Competitive lens

Where OpenCode wins for cited research — and where a rival still belongs in the stack.

OpenCode wins when you want inspectable OSS harness, Plan/Build discipline, and Go open-model pricing; Cursor wins for tab-complete IDE speed.

OpenCode

You want /init + Plan before any file writes
You need Zen or BYOK routing without a closed IDE

Cursor Agent

You live in inline completions and multi-file IDE diffs
Your org mandates Cursor-only procurement

Scores and evidence

Metric lab · 16 dimensions

Click a tile for the editorial note. Color follows score: coral, yellow, mint.

Shape

Avg 91 · 80–98

95Editorial fit

Open-source terminal agent with model freedom — the default we recommend for builders who refuse lock-in.

By group

Fit94

Editorial fit95
Model breadth96
Plan / Build modes91

Cost93

Go plan value92
Value for money93

Trust91

Open source trust98
Privacy posture94
Diff discipline82

Workflow90

Zen gateway quality90
LSP integration90
Multi-session88
Provider flexibility97
Terminal · desktop · IDE92
Share & undo86
Competitive position94
Setup friction80

Benchmark ledger

Public rows are vendor or third-party claims we logged with a date. Desk rows are reserved for VerdictPal self-run results.

VerdictPal-run benches. Completed rows stay in the table; planned checks are collapsed below so unfinished work does not masquerade as evidence.

Measure	Result	Status	Source
/init + Plan then Build on TypeScript monorepo (Go DeepSeek V4 Flash)Plan matched AGENTS.md conventions; Build diffs reviewable with /undo.	Desk hands-on2026-06-15	completeopencode-plan-v1	VerdictPal desk

Planned desk checks (1)

Zen Sonnet route vs raw Anthropic BYOK on ten refactor promptsZen claims benchmarked provider pairing — verify latency and cost per hunk.

Editorial evidence · 1 entry

Task

Run /init + Plan mode on a TypeScript monorepo, then Build the smallest feature with Go-plan DeepSeek V4 Flash.

Desk hands-on: Plan output matched repo conventions after AGENTS.md; Build diffs were reviewable with /undo available.

↳ Time-to-merge, test pass rate, Zen credit burn, wrong-file edits.

Test scenarios · hands-on lab

How we exercised the product. Step through each run before you trust the scores.

Test run

Step 1 of 3

Install opencode; subscribe to Go; /connect

Research log · desk notes

What we learned while building this dossier — not vendor copy.

2026-06-15opencode.ai/docs/zen ↗

Zen retention exceptions documented

Zero-retention on many Zen models; 30-day retention on direct OpenAI/Anthropic BYOK per docs.

What it costs, what it keeps

Pricing deck · checked 2026-09-07

Open source

Software

Bring your own keys
Inspect the harness

Desk pick

$10/mo

Open models bundle
Generous limits

RAW · checked 2026-09-07: OSS agent free · BYOK any provider · OpenCode Go $10/mo (open models, generous limits) · Zen pay-as-you-go credits (from $20 top-up, auto-reload at $5 balance) · team workspaces in beta · card fees passed at cost (4.4% + $0.30)

Privacy deep-dive · checked 2026-09-07

OpenCode states the agent does not store your code or context data. Zen routes prompts to US-hosted providers with zero-retention claims on many models; exceptions include free/promo models (Big Pickle, MiMo-V2.5 Free, Ling 3.0 Flash Fin Free, Nemotron 3 Ultra Free, Nemotron 3.5 Lightning Free, Muse Spark 1.3 Contributor Free) and standard 30-day retention on direct OpenAI/Anthropic API paths. Taste-like project files (AGENTS.md) stay in your repo. Billing via card with fees passed at cost.

Under the hood

Vendors named on the product about page — useful for procurement and privacy reviews.

Taste terminal alt: Command Code
IDE agent: Cursor
Factory orchestration: Factory

Alternatives and context

Alternatives

Cursor Command Code Command Code Factory Warp

Head-to-head

OpenCode vs Cursor OpenCode vs Command Code OpenCode vs Command Code OpenCode vs Factory OpenCode vs Warp

Compare side-by-side → open compare

Workflow roles

How this tool fits into a composed research stack:

open-source coding agentplan-then-build refactorsmulti-provider model routing

Deep panes · 6 lenses

Editorial lenses only. Subscription and API pricing live in their own sections above.

Lens 01

Open source harness

OpenCode is the agent you can read — terminal, desktop beta, and IDE extension share one OSS core with massive community velocity.

Signal: 160K+ GitHub stars cited on site

Pin a release hash for student labs
Read AGENTS.md /init output before trusting plans

Sources and provenance

Source ledger · 5 checked

Product sitechecked 2026-06-15
Docs introchecked 2026-06-15
Zen pricingchecked 2026-09-07
Go planchecked 2026-09-07
Providerschecked 2026-06-15

Quality gate · Flagship

Evidence ready

Verdict history

2026-06-15Shipped OpenCode flagship tool — OSS agent, Go/Zen pricing, Plan/Build modes, and Zen privacy exceptions documented.
2026-09-07Re-checked opencode.ai/go and /docs/zen. Go lists USD 10/mo with no first-month intro on the current page. Zen auto-reload still fires below USD 5 with a USD 20 top-up. Free/promo model privacy exceptions updated.

Related dossiers

Build & code

Cursor

81/100

ROLEAI-native code editor and agentic refactor workspace

VS Code-compatible AI editor with Tab completion, Chat, Agent, MCPs, skills, hooks, cloud agents, Bugbot, Privacy Mode, and team/enterprise governance controls.

Watch outYou cannot enable Privacy Mode or get approval before sending sensitive code to AI providers

Editorial · hands-onFlagship

Developers already livingRepo-wide refactors where

ROLETaste-aware terminal coding agent and open-model harness

Terminal coding agent with continuous taste learning (taste-1), open-model deals, MCP/skills, and subscription credits from $1/mo — ships, tests, and refactors in your conventions.

Watch outYou need a GUI IDE with Tab completion as the primary surface — use Cursor instead

Editorial · hands-onFlagship

Developers who wantBuilders experimenting DeepSeek,

ROLEAgent-native delivery surface

Agent-native software development platform around Droid, with terminal, desktop, CLI, SDK, local/cloud background agents, missions, review workflows, and enterprise controls for delegated software delivery.

Watch outYou only want lightweight VS Code autocomplete

Editorial · hands-onFlagship

Multi-step refactors, migrations,Teams wiring Droid

ROLEAI-native terminal and agentic development workspace

Agentic development environment born from a modern terminal, with Terminal and Agent modes, local/cloud coding agents, third-party CLI agent orchestration, Warp Drive workflows, code review, and enterprise privacy controls.

Watch outYou require a fully local traditional terminal with no account/cloud features

Editorial · hands-onSolid

Developers who wantTeams experimenting local

ROLEPrompt-to-app builder and MVP prototyping tool

AI app-builder that turns natural-language prompts into web apps, projects, code, deployed apps, Lovable Cloud backends, AI Gateway usage, domains, and collaborative team workspaces.

Watch outYou need production-grade security without developer or security review

Editorial · hands-onSolid

Founders, students, productNon-specialists who can

ROLEAI app-development workspace and hosted coding environment

Browser-based AI development platform for building, editing, deploying, collaborating on, and publishing apps with Replit Agent, hosted workspaces, built-in database, authentication, hosting, monitoring, integrations, and usage credits.

Watch outYou need full local control, predictable AI-agent spend, or mature production SRE workflows

Editorial · hands-onSolid

Students solo buildersFast prototype builds

Questions this dossier answers

Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.

What is OpenCode?

Is OpenCode worth using?

OpenCode scores 95 out of 100 on editorial fit and carries Flagship dossier status. Its job in a research workflow is: Open-source terminal coding agent and model-agnostic harness.

Who is OpenCode best for?

OpenCode earns its place when you need:

Developers who want an inspectable open-source agent instead of a closed IDE-only copilot
Teams that need Copilot, ChatGPT, Anthropic BYOK, Zen, Go, or local models in one harness
Students and researchers on a budget using Go or free Zen models with spend caps
Privacy-sensitive repos where vendor storage claims matter — read Zen model exceptions first

When should you not use OpenCode?

Skip OpenCode in these cases:

You need a polished GUI IDE with Tab-as-primary workflow — Cursor may fit better
You will run Build mode on production branches without tests, Plan review, or /undo discipline
You cannot track Zen auto-reload ($20 when balance hits $5) and monthly workspace caps
You need guaranteed EU-only inference on every model without admin model allowlists

What does OpenCode cost?

Open source Free · Go $10/mo · Zen Custom · Teams workspace Free. Pricing last checked 2026-09-07.

Does OpenCode train on your data?

Not recorded as a plan-wide guarantee. Check the dossier's privacy notes and sources.. Privacy terms last checked 2026-09-07.

What goes wrong with OpenCode?

The dossier publishes 6 failure modes for OpenCode, and they stay published whether or not the vendor likes them:

Build mode can apply diffs that pass typecheck but fail course rubrics or security review
Zen free/promo models may retain data for training — Big Pickle, DeepSeek Flash Free, Nemotron Free, etc.
Auto-reload and monthly caps interact confusingly when balance drops below $5
Multi-session parallelism can stomp the same files without branch discipline
Desktop app is still beta — terminal remains the most documented surface
Model deprecation table moves fast — pinned configs break on schedule

What are the alternatives to OpenCode?

The closest options to OpenCode are Cursor, Claude Code, Command Code, Factory, Warp. Each one that has a tool in the atlas is linked from this dossier, with a head-to-head comparison.

The Pack · Editorial newsletter

Know when the rules move.

One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.

The thesis AI checklist is free to use, no signup needed →

Info

Quality gate

Evidence ready
Pricing checked 7 Sep 2026
Privacy checked 7 Sep 2026

What these labels mean

Editorial fit: 0–100 desk score for research-workflow fit. Not stars, not a benchmark.
Evidence level: How close the desk got: self-run, hands-on, synthesized, or vendor claim.
Dossier depth: Flagship, Solid, Lightweight, and Draft describe how finished the page is — not which tool is best.
Verification date: When pricing or privacy was last opened at the source. Not a re-score of the whole dossier.
Benchmark status: Pending means no relevant first-party test is published yet. It is not a negative score.

Open the glossary · Read the methodology

Evidence

Editorial · hands-on

Tested by VerdictPal desk · 2026-06-15

5 sources · 3 bench entries

Verdict history

2026-06-15Shipped OpenCode flagship tool — OSS agent, Go/Zen pricing, Plan/Build modes, and Zen privacy exceptions documented.
2026-09-07Re-checked opencode.ai/go and /docs/zen. Go lists USD 10/mo with no first-month intro on the current page. Zen auto-reload still fires below USD 5 with a USD 20 top-up. Free/promo model privacy exceptions updated.