Item detail
github.com

langchain-ai/langgraph

langchain-ai/langgraph is a developer tool in RepoRadar's Radar section, holding Silver tier and a 'watch' verdict. Its strongest signal is practical usefulness, scored 7.8 out of 10.

Score7.8
Popularity45.4
Riskhigh
TierSilver
Score breakdown
Usefulness7.8
Novelty6.6
Momentum4.3
Maturity6.6
Open-source/build7.4
Evidence7.2
Workflow potential7.8
Setup ease6.5

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

Why it matters

As one of the most-starred agent frameworks (~34.5k stars) and the orchestration backbone of the broader LangChain ecosystem, LangGraph sets de facto patterns for graph-based agent design (state, reducers, checkpointers, interrupts).

Who should use it

Builders Power users

Who should skip it

Skip langchain-ai/langgraph if you cannot isolate its execution environment or audit what data it touches before connecting anything sensitive.

About this signal

langchain-ai/langgraph is tracked by RepoRadar as a developer tool in the Radar section. First seen 2026-06-12; the source record was last checked on 2026-06-12. The current verdict is 'watch' with a Silver tier and review needed setup difficulty. Across RepoRadar's eight signals, langchain-ai/langgraph is strongest on practical usefulness (7.8) and workflow potential (7.8) and weakest on momentum (4.3) — 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 langchain-ai/langgraph record combines a 7.8/10 composite score with separate popularity (45.4), risk (high), and setup (review needed) 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

High risk: do not use without strong containment, approvals, and hands-on review.

Evidence links
Closest alternatives / related signals
Verification record

What RepoRadar actually verified

Tested in a bounded workflow

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-13T10:35:30.621650Z.

passed · cohort-20260712-langgraph-local-routing

Tester
RepoRadar automated local verification harness
Started
2026-07-13T10:35:27.439649Z
Completed
2026-07-13T10:35:30.621650Z
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.
  • Defined typed incident state plus classify, page, and record nodes with an urgent/routine conditional edge.
  • Compiled the graph, invoked it with a checkout-outage fixture, and asserted the urgent branch produced paged-oncall.
  • Executed bounded check: Compile and invoke a conditional LangGraph incident-routing graph over typed local state.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 3.18-second wall time.
Observed results
  • Command exited 0 after 3.18 seconds.
  • LangGraph propagated typed state through classification and selected the urgent page branch for the outage fixture.
  • Expected marker 'CHECK_OK route=urgent action=paged-oncall' was observed in retained output.
  • Validated result.json: 3 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
Observed strengths
  • The graph API made branching control flow explicit and returned the combined route/action state deterministically without a model dependency.
Friction
  • Even this small workflow required explicit state shape, node wiring, conditional labels, and terminal edges; durable agent behavior would add substantially more configuration.
  • Setup or runtime emitted 1 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The deterministic two-branch graph exercises state updates and conditional routing, not checkpointing, interrupts, durable execution, parallel branches, tools, streaming, or an LLM-backed agent.
  • This credential-free disposable workflow does not establish production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The deterministic local LangGraph execution used the open-source package and no LangSmith service or model provider.

Privacy assessment: The synthetic incident text stayed in the local Python process; no tracing service, checkpoint backend, model API, or account was configured.

Open retained test log →

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

49 dated snapshots retained from 2026-06-16 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 score7.8 current · +0.0 net
Repository momentum9.6 current · +5.3 net
GitHub stars (observed)39,628 current · +2,377 net
GitHub stars39,628 exact observation
Version1.2.11
Last release2026-08-11T14:00:50Z
Maintenanceactive
Current riskhigh
Current verdictwatch
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineGoogle Gemini, LangChain, OpenAI

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-137.89.639,628highwatchactive
2026-08-127.89.639,541highwatchactive
2026-08-117.89.639,439highwatchactive
2026-08-107.89.639,356highwatchactive
2026-08-097.89.639,276highwatchactive
2026-08-087.89.639,186highwatchactive
2026-08-077.89.638,749highwatchactive
2026-08-067.84.3Not recordedhighwatchnot recorded
2026-08-057.84.3Not recordedhighwatchnot recorded
2026-08-047.89.638,749highwatchactive
2026-08-037.89.638,749highwatchactive
2026-08-027.89.638,657highwatchactive

Why the record changed

stars changed

Stars changed: 39541 → 39628.

stars changed

Stars changed: 39439 → 39541.

version changed

Version changed: checkpointpostgres==3.1.2 → 1.2.11.

stars changed

Stars changed: 39356 → 39439.

stars changed

Stars changed: 39276 → 39356.

stars changed

Stars changed: 39186 → 39276.

version changed

Version changed: checkpointsqlite==3.1.1 → checkpointpostgres==3.1.2.

stars changed

Stars changed: 38749 → 39186.

stars changed

Stars changed: 38657 → 38749.

stars changed

Stars changed: 38609 → 38657.

stars changed

Source-observed stars changed: 38585 → 38609. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Source-observed stars changed: 38584 → 38585. This reports the retained observation delta and does not infer why the upstream change occurred.