RepoRadar
Leave a Tip
Item detail
github.com

withastro/flue

withastro/flue is a framework in RepoRadar's Agent Frameworks section, holding Gold tier and a 'try now' verdict. Its strongest signal is workflow potential, scored 10.0 out of 10.

Open on GitHub →Back to radar
Score8.8
Popularity76.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum8.0
Maturity8.4
Open-source/build8.4
Evidence7.2
Workflow potential10.0
Setup ease4.2

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

Why it matters

Useful for teams building serious agents beyond scripted demos, especially when they need reusable skills, recovery after failures, and a framework that looks more like operational agent infrastructure than prompt glue.

Who should use it

agent platform teams TypeScript developers AI workflow builders teams moving beyond agent demos

Who should skip it

Skip withastro/flue if the source link, documentation, or setup requirements do not align with your current workflow or stack.

About this signal

withastro/flue is tracked by RepoRadar as a framework in the Agent Frameworks 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 advanced setup difficulty. Across RepoRadar's eight signals, withastro/flue is strongest on workflow potential (10.0) and practical usefulness (9.0) and weakest on setup ease (4.2) — 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 withastro/flue record combines a 8.8/10 composite score with separate popularity (76.0), risk (conditional), and setup (advanced) 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

Flue is designed for autonomous agents with tools, filesystem access, and sandboxed execution, so keep tool allowlists and credentials tightly scoped during any early rollout.

Evidence links
Closest alternatives / related signals
agent-framework typescript skills subagents sandbox
Verification record

What RepoRadar actually verified

Tested in a bounded workflow

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-14T05:27:46.971380Z.

passed · cohort-20260714-flue-local-harness-fs-workflow

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:27:13.535678Z
Completed
2026-07-14T05:27:46.971380Z
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 Flue and Node 22.18 Windows runtime packages with npm lifecycle scripts disabled inside the disposable work directory.
  • Ran Flue init for a Node target, installed a typed Valibot workflow, and invoked it through Flue run with a synthetic marker input.
  • Verified Flue started only its temporary 127.0.0.1 runtime, the harness filesystem round-trip returned the exact marker and length, and no model method was called.
  • Executed bounded check: Initialize a pinned Flue Node project and execute a typed local workflow that writes and reads a synthetic marker through Flue's harness filesystem API.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 33.44-second wall time.
Observed results
  • Command exited 0 after 33.44 seconds.
  • Flue initialized the project and completed the typed local workflow through its CLI, local runtime, and harness.fs adapter with the exact expected result.
  • Expected marker 'CHECK_OK flue=1.0.0-beta.9 init=true run=true loopback=true marker=REPORADAR_FLUE_7319' was observed in retained output.
  • Validated result.json: 6 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
  • Validated transcript.json: 4 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
  • Validated project/flue.config.ts: 2 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
Observed strengths
  • The core workflow runtime provides typed inputs/outputs and a consistent filesystem harness behind a concise local CLI execution path.
Friction
  • Node 24.15 hit a Windows libuv assertion after otherwise successful execution, so this retained run pins Node 22.18.0; model-backed agent behavior remains deliberately untested.
  • Setup or runtime emitted 4 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The workflow validates Flue's init/run CLI path, Valibot schemas, local HTTP runtime, agent registration, and harness.fs plumbing; it deliberately never invokes the declared model, so it does not assess inference, reasoning, durable recovery, remote sandboxes, or provider integration.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The Apache-2.0 Flue package, pinned local Node runtime, and filesystem-only workflow used no account, hosted sandbox, API key, paid model, or inference.

Privacy assessment: Only a synthetic marker traversed the temporary loopback Flue runtime and disposable filesystem; npm package retrieval contacted the registry, but no prompt or fixture reached a model provider.

Open retained test log →

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

46 dated snapshots retained from 2026-06-19 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 score8.8 current · +0.0 net
Repository momentum9.6 current · +1.6 net
GitHub stars (observed)7,863 current · +594 net
GitHub stars7,863 exact observation
Versionv2.0.3
Last release2026-08-05T00:04:42Z
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
2026-08-138.89.67,863conditionaltry nowactive
2026-08-128.89.67,847conditionaltry nowactive
2026-08-118.89.67,812conditionaltry nowactive
2026-08-108.89.67,785conditionaltry nowactive
2026-08-098.89.37,771conditionaltry nowactive
2026-08-088.89.67,762conditionaltry nowactive
2026-08-078.89.67,647conditionaltry nowactive
2026-08-068.88.0Not recordedconditionaltry nownot recorded
2026-08-058.88.0Not recordedconditionaltry nownot recorded
2026-08-048.89.67,647conditionaltry nowactive
2026-08-038.89.67,647conditionaltry nowactive
2026-08-028.89.67,617conditionaltry nowactive

Why the record changed

stars changed

Stars changed: 7847 → 7863.

stars changed

Stars changed: 7812 → 7847.

stars changed

Stars changed: 7785 → 7812.

stars changed

Stars changed: 7771 → 7785.

stars changed

Stars changed: 7762 → 7771.

version changed

Version changed: v2.0.1 → v2.0.3.

stars changed

Stars changed: 7647 → 7762.

stars changed

Stars changed: 7617 → 7647.

stars changed

Stars changed: 7562 → 7617.

version changed

Source-observed version changed: v2.0.0 → v2.0.1. Associated release timestamp: 2026-07-31T07:33:27Z → 2026-08-01T07:48:56Z. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Source-observed stars changed: 7534 → 7562. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Stars changed: 7485 → 7494.