updated 2026-10-09 16:07 UTC

LangWatch

Repository Website

Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.

Observability & Evaluation TypeScript Listed Apache-2.0

Is LangWatch safe? Strong public trust posture, backed by multiple independent signals.

OSSF Scorecard 4.9 / 10
Provenance Attested
Signed commits 83%
Last push today
Advisories None known
Compare LangWatch

How does it stack up against its Observability & Evaluation neighbours?

Pick any agent to compare →
Suggest a correction

In detail: LangWatch scores 83.1/100 (Grade A), ranked #113 of 1371 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 4.9/10; 83% of recent commits are signed; no published advisory affects its latest release (@langwatch/server); last pushed 2026-10-09. Every point is earned from checkable signals — never paid placement. How scoring works →

How LangWatch could raise its score

Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.

Already done? Suggest a correctionAdd the trust badge

Chain of custody

Scanners check what the code says. This traces who ships LangWatch and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.

  1. Source Signed

    github.com/langwatch/langwatch, Apache-2.0, last pushed 2026-10-09. 83% of the last 100 commits carry a verified signature, so changes trace to a verified account.

  2. Review and release Mixed

    OpenSSF Scorecard rates the repository's practices 4.9/10 (scanned Aug 30, 2026, refresh pending). The checks that decide who can get a change released:

    • Code Review2
    • Branch Protection4
    • Signed Releases0
    • Dangerous Workflow0
    • Token Permissions0
    • Pinned Dependencies7
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 4
    CI-Tests 10
    CII-Best-Practices 0
    Code-Review 2
    Contributors 10
    Dangerous-Workflow 0
    Dependency-Update-Tool 10
    Fuzzing 0
    License 10
    Maintained 10
    Packaging 10
    Pinned-Dependencies 7
    SAST 7
    Security-Policy 10
    Signed-Releases 0
    Token-Permissions 0
    Vulnerabilities 0

  3. Published packages Partly attested

    • npm @langwatch/server Source link points back to this repo Build provenance attested
    • PyPI langwatch Source link isn't a GitHub repo No build attestation

  4. What you install today No known advisories

    Latest release checked: @langwatch/server 3.20.1. No published advisory affects it (OSV, checked 2026-10-09).

Changes to this chain

  • 2026-08-30 OSSF Scorecard: 4.9/10

Evidence behind this score

Coverage A: 4 of 5 independent evidence types found.

  • GitHub repository data
  • Package downloads
  • Supply-chain checks
  • Public actions (missing)
  • Community mentions

Verify this score yourself

Every build re-issues LangWatch’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.

Signed credential (JSON) How to verify

What this score doesn’t check

It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.

How LangWatch compares in Observability & Evaluation

  1. #3 OpenLLMetry 86.1 +3.0
  2. #4 Weights & Biases Weave 84.3 +1.2
  3. #5 LangWatch 83.1 this agent
  4. #6 Langfuse 79.8 −3.3
  5. #7 Evidently 78.9 −4.2

Bars show each HVTrust score; the tick marks LangWatch’s 83.1.

Where the 83.1 comes from

HVTrust dimensions vs the Observability & Evaluation average

83.1 / 100 · 100.0% confidence

LangWatch Observability & Evaluation average (26 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
17.8 / 25
6.6 above avg 11.2
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
4.7 above avg 13.3
Transparency50% declared license · 50% OSSF Scorecard
12.7 / 17
0.7 above avg 12.0
Maintenance60% last-push freshness · 40% commit activity
20.0 / 20
4.7 above avg 15.3
AdoptionLog-scaled stars · package downloads
15.5 / 20
2.1 above avg 13.4

Quick Trust Read

What Would Improve It
Improve safety / integrity to lift the weakest part of the trust profile.
Recent Changes
2026-09-23
Rank Moved
Rank dropped 42 spots (#63 → #105)
2026-09-21
Rank Moved
Rank rose 44 spots (#107 → #63)
2026-09-10
Provider Added
Runtime surface grew — new detected provider dependency: ElevenLabs
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 4.9/10. Tighten the weakest checks to improve public safety evidence.
Compare with Promptfoo Get email alerts for LangWatch View Observability & Evaluation Report missing data
84.3
Activity sub-score · out of 100
#5
In Observability & Evaluation

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-10-09 16:07 UTC · Repo last pushed today

Rank Trend

2026-09-29 2026-10-09

Activity & Reach

Stars
4.9k
Forks
409
Last Push
2026-10-09
today
Commits (4 wk)
236
Downloads (7d)
90,049
pypi
HN mentions (30d)
1
Open Issues
56
Rank Change
=
was #113

Analysis

Activity Inputs

84.3 / 100
StarsRepository reach
22.2 / 30
FreshnessLast push recency
25.0 / 25
ActivityRecent commits
25 / 25
CommunityFork signal
12.1 / 20

Common questions about LangWatch

Public supply-chain signals for LangWatch are strong: it has multiple independent trust indicators in place. This does not replace your own security review, but LangWatch carries less obvious unverified-evidence risk than projects with thin signals.
Does LangWatch publish package provenance?
Yes. LangWatch's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does LangWatch have an OpenSSF Scorecard?
LangWatch has an OpenSSF Scorecard score of 4.9/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is LangWatch actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does LangWatch use?
LangWatch ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are LangWatch's commits signed?
83% of the last 100 commits to LangWatch are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

Compare LangWatch head-to-head

LangWatch vs Promptfoo → LangWatch vs MLflow → LangWatch vs OpenLLMetry →

AI agent surface

MCP, providers, tool surface
Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
high confidence
Implemented
LangWatch appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
6 detected
Public provider/service dependencies detected.
Credential signal: API keys or service config markers documented.
Tool / Plugin Surface
high confidence
Declared
Declared plugin/integration surface detected.
  • database
Detailed evidence is not shown in the public view.
Package Provenance Drift
medium confidence
Partial
Some package metadata matches; some source metadata is missing
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live
How this surface has changed

Detected changes to LangWatch's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.

2026-09-10
Provider Added
Runtime surface grew — new detected provider dependency: ElevenLabs
2026-09-02
Provider Added
Runtime surface grew — new detected provider dependencies: Anthropic, Postgres, Redis

Maintain LangWatch?

For maintainers

HVTrust scores LangWatch from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history
Rank 10HVTrust 2Surface 2Grade 1Scorecard 1
2026-09-23
Rank Moved
Rank dropped 42 spots (#63 → #105)
2026-09-21
Rank Moved
Rank rose 44 spots (#107 → #63)
2026-09-10
Provider Added
Runtime surface grew — new detected provider dependency: ElevenLabs
2026-09-10
Rank Moved
Rank dropped 10 spots (#92 → #102)
2026-09-08
Rank Moved
Rank rose 38 spots (#130 → #92)
2026-09-08
HVTrust Changed
HVTrust up 3.0pts (80.2 → 83.2)
2026-09-07
Rank Moved
Rank dropped 42 spots (#88 → #130)
2026-09-05
Rank Moved
Rank dropped 21 spots (#70 → #91)
2026-09-02
Provider Added
Runtime surface grew — new detected provider dependencies: Anthropic, Postgres, Redis
2026-09-02
Rank Moved
Rank dropped 11 spots (#58 → #69)
2026-08-30
Scorecard Added
OSSF Scorecard: 4.9/10
2026-08-30
Grade Changed
Trust grade B → A
2026-08-30
Rank Moved
Rank rose 70 spots (#122 → #52)
2026-08-30
HVTrust Changed
HVTrust up 9.6pts (75.7 → 85.3)
2026-08-26
Rank Moved
Rank dropped 13 spots (#90 → #103)
2026-07-13
Rank Moved
Rank dropped 10 spots (#67 → #77)
GitHub → Website → PyPI: langwatch npm: @langwatch/server

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 83.1 Grade A
Markdown:
[![HVTrust](https://hvtracker.net/badge/langwatch.svg)](https://hvtracker.net/agents/langwatch)
HTML:
<a href="https://hvtracker.net/agents/langwatch"><img src="https://hvtracker.net/badge/langwatch.svg" alt="HVTrust"></a>

Other agents in Observability & Evaluation

Data sources
GitHub REST API (repo, commits, stars, forks, license) · npm Registry (downloads, provenance) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON