RepoRadar
Leave a Tip
Item detail
github.com

colbymchenry/codegraph

colbymchenry/codegraph is a developer tool that RepoRadar is tracking in its Radar section, currently rated Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 9.9 out of 10.

Open on GitHub →Back to radar
Score8.8
Popularity57.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty7.0
Momentum8.0
Maturity8.0
Open-source/build8.4
Evidence7.2
Workflow potential9.9
Setup ease6.4

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

Why it matters

Useful for teams using coding agents on large repositories who want faster repo understanding and less context waste without shipping their indexing layer to a hosted service.

Who should use it

developers using coding agents teams working in large codebases local AI users who want source to stay on-device tooling builders improving agent context retrieval

Who should skip it

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

About this signal

colbymchenry/codegraph is tracked by RepoRadar as a developer tool 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. colbymchenry/codegraph leads on workflow potential (9.9) and practical usefulness (9.0); its lowest signal is setup ease (6.4), so factor that in before investing setup time. 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 colbymchenry/codegraph record combines a 8.8/10 composite score with separate popularity (57.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.

Risk explanation

It can surface private source structure and code context to whichever coding agent you connect, so pair it with models and providers that match your code-handling requirements.

Evidence links
Closest alternatives / related signals
ai-coding knowledge-graph code-search local-ai developer-tools
Verification record

What RepoRadar actually verified

Tested in a bounded workflow

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-14T00:53:20.015967Z.

passed · cohort-20260713-codegraph-local-index-query-workflow

Tester
RepoRadar automated local verification harness
Started
2026-07-14T00:53:12.672655Z
Completed
2026-07-14T00:53:20.015967Z
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.
  • Disabled CodeGraph telemetry inside the disposable home before indexing any fixture content.
  • Indexed two linked JavaScript source modules, inspected JSON status and file output, and queried the exported normalizeIncident function by kind.
  • Executed bounded check: Disable telemetry, index a disposable two-module JavaScript project with CodeGraph, and query a named exported function from the local graph.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 7.34-second wall time.
Observed results
  • Command exited 0 after 7.34 seconds.
  • CodeGraph indexed exactly two source files and returned normalizeIncident from src/incident.js through its JSON symbol-query interface.
  • Expected marker 'CHECK_OK query=normalizeIncident source_files=2 indexed=true telemetry=off' was observed in retained output.
  • Validated result.json: 4 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
Observed strengths
  • The self-contained Windows package completed local parsing, reference resolution, WAL-backed indexing, file inventory, and symbol lookup with telemetry disabled.
Friction
  • The package includes a bundled runtime and persistent SQLite index inside the disposable project; this small run did not exercise its MCP installer or background daemon.
Limitations
  • The two-file fixture validates local initialization, parsing, reference resolution, status, file listing, and symbol query only; it does not cover a large monorepo, incremental sync, MCP clients, agent configuration, every supported language, or concurrent queries.
  • 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 CodeGraph 1.4.1 npm package ran locally with no paid plan, agent, model, or hosted indexing service.

Privacy assessment: Telemetry was explicitly disabled before initialization; only two synthetic JavaScript modules were indexed inside the disposable work directory.

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 score8.8 current · +0.0 net
Repository momentum10.0 current · +2.0 net
GitHub stars (observed)66,276 current · +6,491 net
GitHub stars66,276 exact observation
Versionv1.5.0
Last release2026-07-21T19:15:36Z
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
2026-08-138.810.066,276conditionaltry nowactive
2026-08-128.810.066,082conditionaltry nowactive
2026-08-118.810.065,862conditionaltry nowactive
2026-08-108.810.065,673conditionaltry nowactive
2026-08-098.810.065,525conditionaltry nowactive
2026-08-088.810.065,387conditionaltry nowactive
2026-08-078.810.064,198conditionaltry nowactive
2026-08-068.88.0Not recordedconditionaltry nownot recorded
2026-08-058.88.0Not recordedconditionaltry nownot recorded
2026-08-048.810.064,198conditionaltry nowactive
2026-08-038.810.064,198conditionaltry nowactive
2026-08-028.810.064,039conditionaltry nowactive

Why the record changed

stars changed

Stars changed: 66082 → 66276.

stars changed

Stars changed: 65862 → 66082.

stars changed

Stars changed: 65673 → 65862.

stars changed

Stars changed: 65525 → 65673.

stars changed

Stars changed: 65387 → 65525.

stars changed

Stars changed: 64198 → 65387.

stars changed

Stars changed: 64039 → 64198.

stars changed

Stars changed: 63920 → 64039.

stars changed

Source-observed stars changed: 63867 → 63920. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Source-observed stars changed: 63866 → 63867. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Source-observed stars changed: 63865 → 63866. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Stars changed: 63005 → 63261.