← Leaderboard
7.4 L3

Sourcegraph

Ready Assessed · Docs reviewed · Mar 21, 2026 Confidence 0.53 Last evaluated Mar 21, 2026

Verify before you commit

Trust read first, source links second, build decision third.

Use this page to sanity-check Sourcegraph quickly. We surface the evidence tier, freshness, and failure posture here, then put the official links where you can actually act on them, especially on mobile.

Evidence

Assessed

Docs reviewed · Mar 21, 2026

Freshness

Updated 2026-03-21T02:16:09.54205+00:00

Mar 21, 2026

Failures

Clear

No active failures listed

Score breakdown

Dimension Score Bar
Execution Score

Measures reliability, idempotency, error ergonomics, latency distribution, and schema stability.

7.6
Access Readiness Score

Measures how easily an agent can onboard, authenticate, and start using this service autonomously.

6.9
Aggregate AN Score

Composite score: 70% execution + 30% access readiness.

7.4

Autonomy breakdown

P1 Payment Autonomy
G1 Governance Readiness
W1 Web Agent Accessibility
Overall Autonomy
Pending

Active failure modes

No active failure modes reported.

Reviews

Published review summaries with trust provenance attached to each card.

How are reviews sourced?

Docs-backed Built from public docs and product materials.

Test-backed Backed by guided testing or evaluator-run checks.

Runtime-verified Verified from authenticated runtime evidence.

Sourcegraph: API Design & Integration Surface

Docs-backed

The GraphQL API covers code search (with Sourcegraph's query language), repository management, code intelligence (definitions, references, hover information), and batch changes (automated PRs across repositories). The search API is the primary agent integration surface — agents submit structured search queries and receive matching code locations, file contents, and repository context. Batch Changes enables agents to programmatically generate and track multi-repository code modifications.

Rhumb editorial team Mar 21, 2026

Sourcegraph: Error Handling & Operational Reliability

Docs-backed

Reliability for Sourcegraph Cloud is vendor-managed. Self-hosted Sourcegraph reliability is the team's operational responsibility — the platform requires indexing infrastructure that scales with repository count and size. The search infrastructure is designed for high-throughput query patterns appropriate for agent-driven analysis workflows.

Rhumb editorial team Mar 21, 2026

Sourcegraph: Comprehensive Agent-Usability Assessment

Docs-backed

Sourcegraph is a code intelligence and search platform that enables cross-repository search and analysis at scale — finding all usages of a function across 1000 repos, searching for security-vulnerable patterns across a codebase, or tracking how APIs are adopted across an organization's repositories. For agents involved in codebase analysis, security scanning, or automated refactoring, Sourcegraph's GraphQL API provides programmatic access to the search and code intelligence layer that manual text search cannot practically deliver at scale.

Rhumb editorial team Mar 21, 2026

Sourcegraph: Auth & Access Control

Docs-backed

Authentication uses access tokens for the GraphQL API. Sourcegraph access tokens provide access to repositories configured in the Sourcegraph instance. For Sourcegraph Cloud, teams use personal access tokens; for self-hosted instances, service accounts with appropriate repository access are the appropriate automation credential.

Rhumb editorial team Mar 21, 2026

Sourcegraph: Documentation & Developer Experience

Docs-backed

Documentation is comprehensive and the GraphQL API is self-documenting with introspection. The search query language documentation is thorough — agents building code search capabilities should invest time in the query language reference to build effective searches. The Batch Changes documentation covers the programmatic multi-repo modification pattern clearly.

Rhumb editorial team Mar 21, 2026

Use in your agent

mcp
get_score ("sourcegraph")
● Sourcegraph 7.4 L3 Ready
exec: 7.6 · access: 6.9

Trust shortcuts

This score is documentation-derived. Treat it as a docs-based evaluation of API design, auth, error handling, and documentation quality.

Read how the score works, how disputes are handled, and how Rhumb scored itself before launch.

Overall tier

L3 Ready

7.4 / 10.0

Alternatives

No alternatives captured yet.