RepoRadar
Leave a tipDaily brief
Item detail
github.com

openai/openai-agents-js

openai/openai-agents-js is a framework in RepoRadar's Developer Tools section, holding Gold tier and a 'try now' verdict. Its strongest signal is workflow potential, scored 10.0 out of 10.

Produced and maintained by RepoRadar Research · Methodology · Corrections.

Open on GitHub →Back to radar
Score8.8
Popularity71.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty7.0
Momentum8.0
Maturity8.3
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 JavaScript and TypeScript teams that want an official agent framework with tracing and guardrails instead of stitching together tool use, orchestration, and voice flows by hand.

Where this stands now

openai/openai-agents-js ranks #2 of 1014 tracked Developer Tools items by composite score (8.8 against a section median of 4.9). The section currently carries 784 Bronze, 126 Silver, 103 Gold, 1 Low Signal. RepoRadar has retained observations for this record since 2026-06-19 (100 days in the current window). Signal extremes versus the section: momentum at the 96th percentile; novelty at the 86th percentile.

Who should use it

JavaScript developers TypeScript developers voice-agent builders teams building agent products

Who should skip it

Pass on openai/openai-agents-js if its scope or audience does not match what your team is building right now.

About this signal

openai/openai-agents-js is tracked by RepoRadar as a framework in the Developer Tools section. First seen 2026-06-19; the source record was last checked on 2026-06-19. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, openai/openai-agents-js is strongest on workflow potential (10.0) and practical usefulness (9.0) and weakest on setup ease (6.4) — a profile worth weighing against your own priorities. 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 openai/openai-agents-js record combines a 8.8/10 composite score with separate popularity (71.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Questions worth asking before you adopt this

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

The SDK is designed to broker tool calls, MCP servers, and realtime/voice flows into external systems, so start with least-privilege credentials and explicit human approval on any side-effecting actions.

Evidence links
Closest alternatives / related signals
openai agent-sdk typescript voice-agents multi-agent
Verification record

What RepoRadar actually verified

Tested in a bounded workflow Source-only update since test

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-14T04:55:56.528112Z.

A source release dated 2026-09-10 is newer than the retained test dated 2026-07-14; the previous test may no longer represent the current release.

Read as a sequence: 1 retained check(s) on 2026-07-14 with outcomes of 1 passed; evidence scopes covered bounded representative workflows. Recorded setup time totals 1 minute(s).

passed · cohort-20260713-openai-agents-js-deterministic-tool-workflow

Tester
RepoRadar automated local verification harness
Started
2026-07-14T04:55:43.977325Z
Completed
2026-07-14T04:55:56.528112Z
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 3 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed pinned OpenAI Agents JS and Zod packages with lifecycle scripts disabled and tracing disabled for the run.
  • Provided an in-memory Model that inspected the SDK-serialized tool definition and returned one deterministic function-call item.
  • Executed the SDK function tool against one allowlisted fixture path, stopped on its output, and retained request/call counts plus the final output.
  • Executed bounded check: Run an OpenAI Agents JS agent with an in-memory Model implementation that emits one function call, execute the allowlisted fixture-read tool, and stop on its output.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 12.55-second wall time.
Observed results
  • Command exited 0 after 12.55 seconds.
  • The Agents JS runner serialized the function tool, accepted the model's function-call item, invoked the tool exactly once, and promoted its marker output to the final result.
  • Expected marker 'CHECK_OK model_requests=1 tool_calls=1 final=REPORADAR_AGENTS_JS_FIXTURE_7319' was observed in retained output.
  • Validated result.json: 5 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
Observed strengths
  • The Model interface and stop-on-first-tool behavior support a fully deterministic test of the real agent runner and tool execution path with tracing and network model calls absent.
Friction
  • A custom Model must emit the SDK's typed function-call item shape and usage object; provider-specific request/response behavior remains outside this local runner check.
  • Setup or runtime emitted 2 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The custom deterministic Model proves the SDK runner and function-tool loop without a hosted model; it does not measure OpenAI model quality, provider transport, streaming, handoffs, guardrails, approval flows, or trace export.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The pinned MIT SDK and in-memory model ran locally with no OpenAI API request, token charge, account, or hosted trace export.

Privacy assessment: Only a synthetic fixture was read by the allowlisted local tool; dependency installation contacted npm, while tracing was disabled and no content was sent to a provider.

Open retained test log →

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

79 dated snapshots retained from 2026-06-19 through 2026-09-27; 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 score8.8 current · +0.0 net
Repository momentum9.3 current · +1.3 net
GitHub stars (observed)3,861 current · +471 net
GitHub stars3,861 exact observation
Versionv0.18.0
Last release2026-09-10T21:23:58Z
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
2026-09-278.89.33,861ConditionalTry nowActive
2026-09-268.89.33,859ConditionalTry nowActive
2026-09-258.88.53,857ConditionalTry nowActive
2026-09-248.89.33,858ConditionalTry nowActive
2026-09-238.89.33,853ConditionalTry nowActive
2026-09-228.89.03,850ConditionalTry nowActive
2026-09-218.89.03,843ConditionalTry nowActive
2026-09-208.89.33,836ConditionalTry nowActive
2026-09-198.89.03,835ConditionalTry nowActive
2026-09-178.89.03,829ConditionalTry nowActive
2026-09-158.89.33,820ConditionalTry nowActive
2026-09-138.89.03,802ConditionalTry nowActive

Why the record changed

Stars change

Stars changed: 3859 → 3861.

Stars change

Stars changed: 3857 → 3859.

Stars change

Stars changed: 3858 → 3857.

Stars change

Stars changed: 3855 → 3858.

Stars change

Stars changed: 3853 → 3855.

Stars change

Stars changed: 3850 → 3853.

Stars change

Stars changed: 3845 → 3850.

Stars change

Stars changed: 3843 → 3845.

Stars change

Stars changed: 3837 → 3843.

Stars change

Stars changed: 3836 → 3837.

Stars change

Stars changed: 3835 → 3836.

Stars change

Stars changed: 3833 → 3835.