@anthropic-ai/claude-agent-sdk

Name: @anthropic-ai/claude-agent-sdk
Rating: 3.24 (1 reviews)
Author: wolffiex

#804 · by wolffiex

agent tool-use multi-step

3.24/ 5.00

trustedBeta

Mar 3, 2026 at 7:21 AM6 signals analysed68 commits (90d)No manual reviews · fully automated

Trust Signal Breakdown

high3 sub-signals across 6 dimensions

CVEs, dependency health, and supply chain integrity

3 of 3 sub-signals with data

Known CVEs40%5.0

No known CVEs

via OSV.dev

Dependency Health30%5.0

0 dependencies (minimal)

via npm / PyPI

Supply Chain30%5.0

Dependency count known but no supply chain scan yet

via npm provenance

Uptime, latency, error rates, and incident history

0 of 0 sub-signals with data

Commit recency, release cadence, issue response, CI/CD

0 of 0 sub-signals with data

Downloads, stars, dependents, and growth trajectory

0 of 0 sub-signals with data

License, documentation, security policy, changelog

0 of 0 sub-signals with data

Track record, org maturity, community standing

0 of 0 sub-signals with data

About this score

Scored across 3 sub-signals in 6 dimensionsScoring engine v1 (beta) — actively being expandedPhase 1: Core sub-signal architecture (live)Phase 2: Permission scope & expanded collection (in progress)

Trust AssessmentAI Assessment

SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.

Package Availability (30d)

100.00%

p50: 157ms · p99: 206ms

Avg Latency

134ms

averaged across 30d health checks

Weekly Downloads

2.4M+3%

npm weekly

Transparency & Compliance3/5 passed

✓

Open Source CodePublic repository on GitHub