RepoRadar
Leave a Tip
Item detail
github.com

anomalyco/opencode

anomalyco/opencode is an agent project in RepoRadar's Radar section, holding Gold tier and a 'try now' verdict. Its strongest signal is momentum, scored 10.0 out of 10.

Open on GitHub →Back to radar
Score9.3
Popularity38.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum10.0
Maturity7.9
Open-source/build8.4
Evidence7.2
Workflow potential10.0
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for developers who want a serious open coding-agent stack they can run, inspect, and adapt without locking the workflow inside one proprietary IDE.

Who should use it

developers evaluating open coding agents teams that want a self-directed code assistant outside one IDE builders comparing Claude Code, Codex, OpenCode, and similar workflows power users who want more control than closed hosted coding tools allow

Who should skip it

Skip anomalyco/opencode if the source repository or demo is inactive, unmaintained, or no longer matches the description shown here.

About this signal

anomalyco/opencode is tracked by RepoRadar as an agent project in the Radar section. First seen 2026-06-20; the source record was last checked on 2026-06-20. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for anomalyco/opencode are momentum (10.0) and workflow potential (10.0), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The anomalyco/opencode record combines a 9.3/10 composite score with separate popularity (38.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

It can plan and change code inside real repositories, so review filesystem access, generated patches, and any linked credentials before using it on sensitive projects.

Evidence links
Closest alternatives / related signals
coding-agent cli developer-tool open-source code-assistant
Verification record

What RepoRadar actually verified

Tested in a bounded workflow

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-14T05:16:46.997071Z.

partial · cohort-20260712-opencode-isolated

Tester
RepoRadar automated local verification harness
Started
2026-07-13T03:20:19.560977Z
Completed
2026-07-13T03:20:27.207233Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
0 minute(s)
Evidence scope
Bounded setup or capability check
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Executed bounded check: Resolve and launch the OpenCode CLI package.
  • Captured the complete sanitized stdout, stderr, exit status, and 7.65-second wall time.
Observed results
  • Command exited 0 after 7.65 seconds.
  • The command produced a successful local process exit; complete output is retained.
Observed strengths
  • The pinned [email protected] package resolved in the isolated npm cache, launched, and reported version 1.17.18.
Friction
  • No blocking friction was observed during this bounded local check.
Limitations
  • Only package resolution and version startup were checked; no provider or coding task was configured.
  • This bounded cohort check is not a production benchmark or a claim of real user-workflow adoption.

Pricing assessment: No paid plan or metered provider usage was exercised; package or licensing, hosting, and provider costs remain workflow-dependent.

Privacy assessment: No repository content, user data, or provider prompt was transmitted; broader product data handling was not assessed by this bounded run.

Open retained test log →

failed · cohort-20260714-opencode-local-read-agent-workflow

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:05:03.866192Z
Completed
2026-07-14T05:05:10.287906Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded setup or capability check
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 4 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned official [email protected] package with lifecycle scripts disabled inside the disposable work directory.
  • Bound a deterministic OpenAI-compatible fixture server to an operating-system-assigned 127.0.0.1 port and configured the CLI to deny non-read tools.
  • Prompted the CLI to read one synthetic marker through its built-in read tool, then asserted exactly two streamed /v1/chat/completions requests.
  • Verified the second request contained the actual tool output, the final CLI output contained the mock's exact response, and the fixture hash was unchanged.
  • Executed bounded check: Run OpenCode's official CLI against a loopback-only deterministic model that requests its built-in read tool, then verify the real tool result reaches the second model turn.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 6.42-second wall time.
Observed results
  • Check exited 1 after 6.42 seconds; failure output is retained and the verification stage must not advance.
Observed strengths
  • No product strength was established in this failed attempt; diagnostic evidence is retained.
Friction
  • A deterministic protocol fixture required product-specific isolation flags and provider configuration; real model behavior, authentication, latency, and cost remain deliberately outside this check.
  • Setup or runtime emitted 16 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The local mock validates OpenCode's provider wire path, agent loop, tool schema, built-in read execution, and final event output; it does not measure hosted-model quality, authentication, provider reliability, interactive UX, long tasks, or write-tool safety.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The CLI and loopback model fixture used no account, subscription, API credit, or paid inference; npm was contacted only to retrieve the pinned package.

Privacy assessment: Only a synthetic marker was read and sent to a server bound to 127.0.0.1; package installation contacted npm, while no prompt or fixture content was sent to a model provider.

Open retained test log →

failed · cohort-20260714-opencode-local-read-agent-workflow-v2

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:06:00.231020Z
Completed
2026-07-14T05:07:07.346891Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
2 minute(s)
Evidence scope
Bounded setup or capability check
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 4 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned official [email protected] package with lifecycle scripts disabled inside the disposable work directory.
  • Bound a deterministic OpenAI-compatible fixture server to an operating-system-assigned 127.0.0.1 port and configured the CLI to deny non-read tools.
  • Prompted the CLI to read one synthetic marker through its built-in read tool, then asserted exactly two streamed /v1/chat/completions requests.
  • Verified the second request contained the actual tool output, the final CLI output contained the mock's exact response, and the fixture hash was unchanged.
  • Executed bounded check: Run OpenCode's official CLI against a loopback-only deterministic model that requests its built-in read tool, then verify the real tool result reaches the second model turn.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 67.12-second wall time.
Observed results
  • Check exited 1 after 67.12 seconds; failure output is retained and the verification stage must not advance.
Observed strengths
  • No product strength was established in this failed attempt; diagnostic evidence is retained.
Friction
  • A deterministic protocol fixture required product-specific isolation flags and provider configuration; real model behavior, authentication, latency, and cost remain deliberately outside this check.
  • Setup or runtime emitted 13 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The local mock validates OpenCode's provider wire path, agent loop, tool schema, built-in read execution, and final event output; it does not measure hosted-model quality, authentication, provider reliability, interactive UX, long tasks, or write-tool safety.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The CLI and loopback model fixture used no account, subscription, API credit, or paid inference; npm was contacted only to retrieve the pinned package.

Privacy assessment: Only a synthetic marker was read and sent to a server bound to 127.0.0.1; package installation contacted npm, while no prompt or fixture content was sent to a model provider.

Open retained test log →

failed · cohort-20260714-opencode-local-read-agent-workflow-v3

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:14:37.465907Z
Completed
2026-07-14T05:14:48.227927Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded setup or capability check
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 4 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned official [email protected] package with lifecycle scripts disabled inside the disposable work directory.
  • Bound a deterministic OpenAI-compatible fixture server to an operating-system-assigned 127.0.0.1 port and configured the CLI to deny non-read tools.
  • Prompted the CLI to read one synthetic marker through its built-in read tool, then asserted exactly two streamed /v1/chat/completions requests.
  • Verified the second request contained the actual tool output, the final CLI output contained the mock's exact response, and the fixture hash was unchanged.
  • Executed bounded check: Run OpenCode's official CLI against a loopback-only deterministic model that requests its built-in read tool, then verify the real tool result reaches the second model turn.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 10.76-second wall time.
Observed results
  • Check exited 1 after 10.76 seconds; failure output is retained and the verification stage must not advance.
Observed strengths
  • No product strength was established in this failed attempt; diagnostic evidence is retained.
Friction
  • A deterministic protocol fixture required product-specific isolation flags and provider configuration; real model behavior, authentication, latency, and cost remain deliberately outside this check.
  • Setup or runtime emitted 13 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The local mock validates OpenCode's provider wire path, agent loop, tool schema, built-in read execution, and final event output; it does not measure hosted-model quality, authentication, provider reliability, interactive UX, long tasks, or write-tool safety.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The CLI and loopback model fixture used no account, subscription, API credit, or paid inference; npm was contacted only to retrieve the pinned package.

Privacy assessment: Only a synthetic marker was read and sent to a server bound to 127.0.0.1; package installation contacted npm, while no prompt or fixture content was sent to a model provider.

Open retained test log →

failed · cohort-20260714-opencode-local-read-agent-workflow-v4

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:15:32.888643Z
Completed
2026-07-14T05:15:42.681822Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded setup or capability check
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 4 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned official [email protected] package with lifecycle scripts disabled inside the disposable work directory.
  • Bound a deterministic OpenAI-compatible fixture server to an operating-system-assigned 127.0.0.1 port and configured the CLI to deny non-read tools.
  • Prompted the CLI to read one synthetic marker through its built-in read tool, then asserted exactly two streamed /v1/chat/completions requests.
  • Verified the second request contained the actual tool output, the final CLI output contained the mock's exact response, and the fixture hash was unchanged.
  • Executed bounded check: Run OpenCode's official CLI against a loopback-only deterministic model that requests its built-in read tool, then verify the real tool result reaches the second model turn.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 9.79-second wall time.
Observed results
  • Check exited 1 after 9.79 seconds; failure output is retained and the verification stage must not advance.
Observed strengths
  • No product strength was established in this failed attempt; diagnostic evidence is retained.
Friction
  • A deterministic protocol fixture required product-specific isolation flags and provider configuration; real model behavior, authentication, latency, and cost remain deliberately outside this check.
  • Setup or runtime emitted 13 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The local mock validates OpenCode's provider wire path, agent loop, tool schema, built-in read execution, and final event output; it does not measure hosted-model quality, authentication, provider reliability, interactive UX, long tasks, or write-tool safety.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The CLI and loopback model fixture used no account, subscription, API credit, or paid inference; npm was contacted only to retrieve the pinned package.

Privacy assessment: Only a synthetic marker was read and sent to a server bound to 127.0.0.1; package installation contacted npm, while no prompt or fixture content was sent to a model provider.

Open retained test log →

passed · cohort-20260714-opencode-local-read-agent-workflow-v5

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:16:39.048765Z
Completed
2026-07-14T05:16:46.997071Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded representative workflow
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 4 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned official [email protected] package with lifecycle scripts disabled inside the disposable work directory.
  • Bound a deterministic OpenAI-compatible fixture server to an operating-system-assigned 127.0.0.1 port and configured the CLI to deny non-read tools.
  • Prompted the CLI to read one synthetic marker through its built-in read tool, then asserted exactly two streamed /v1/chat/completions requests.
  • Verified the second request contained the actual tool output, the final CLI output contained the mock's exact response, and the fixture hash was unchanged.
  • Executed bounded check: Run OpenCode's official CLI against a loopback-only deterministic model that requests its built-in read tool, then verify the real tool result reaches the second model turn.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 7.95-second wall time.
Observed results
  • Command exited 0 after 7.95 seconds.
  • OpenCode exposed and executed its built-in read tool once, returned the synthetic marker to the loopback model, completed the second turn, and left the fixture byte-identical.
  • Expected marker 'CHECK_OK cli=opencode requests=2 tool=read unchanged=true' was observed in retained output.
  • Validated result.json: 9 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
  • Validated transcript.json: 3 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
Observed strengths
  • The official CLI completed a full provider-to-tool-to-provider agent turn with an allowlisted built-in read tool and machine-readable output, without an account or hosted model.
Friction
  • A deterministic protocol fixture required product-specific isolation flags and provider configuration; real model behavior, authentication, latency, and cost remain deliberately outside this check.
  • Setup or runtime emitted 4 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The local mock validates OpenCode's provider wire path, agent loop, tool schema, built-in read execution, and final event output; it does not measure hosted-model quality, authentication, provider reliability, interactive UX, long tasks, or write-tool safety.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The CLI and loopback model fixture used no account, subscription, API credit, or paid inference; npm was contacted only to retrieve the pinned package.

Privacy assessment: Only a synthetic marker was read and sent to a server bound to 127.0.0.1; package installation contacted npm, while no prompt or fixture content was sent to a model provider.

Open retained test log →

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

45 dated snapshots retained from 2026-06-20 through 2026-08-13; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score9.3 current · +0.0 net
Repository momentum10.0 current · +0.0 net
GitHub stars (observed)197,042 current · +11,466 net
GitHub stars197,042 exact observation
Versionv1.18.18
Last release2026-08-13T01:15:04Z
Maintenanceactive
Current riskconditional
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-139.310.0197,042conditionaltry nowactive
2026-08-129.310.0196,508conditionaltry nowactive
2026-08-119.310.0196,020conditionaltry nowactive
2026-08-109.310.0195,631conditionaltry nowactive
2026-08-099.310.0195,244conditionaltry nowactive
2026-08-089.310.0194,916conditionaltry nowactive
2026-08-079.310.0192,655conditionaltry nowactive
2026-08-069.310.0Not recordedconditionaltry nownot recorded
2026-08-059.310.0Not recordedconditionaltry nownot recorded
2026-08-049.310.0192,655conditionaltry nowactive
2026-08-039.310.0192,655conditionaltry nowactive
2026-08-029.310.0192,214conditionaltry nowactive

Why the record changed

version changed

Version changed: v1.18.16 → v1.18.18.

stars changed

Stars changed: 196508 → 197042.

stars changed

Stars changed: 196020 → 196508.

stars changed

Stars changed: 195631 → 196020.

stars changed

Stars changed: 195244 → 195631.

version changed

Version changed: v1.18.15 → v1.18.16.

stars changed

Stars changed: 194916 → 195244.

stars changed

Stars changed: 192655 → 194916.

version changed

Version changed: v1.18.11 → v1.18.15.

stars changed

Stars changed: 192214 → 192655.

version changed

Version changed: v1.18.10 → v1.18.11.

stars changed

Stars changed: 191821 → 192214.