The open-source talent graph for humans and AI agents. Discover public developers and request consent-gated introductions.
DevGlobe provides 7 well-named tools with clear verb-noun patterns (search_developers, get_developer_profile, find_similar_developers, match_developers_to_repository, find_trending_developers, find_mission_opportunities, request_introduction). All tools have descriptions (avg 150 chars, within 10-1024 baseline). Input schemas are present with type definitions and parameter descriptions. However, output schemas are not documented, LLMs cannot predict response structure for downstream chaining. Error handling guidance is absent; tools lack recovery hints. The request_introduction tool (WRITE risk) lacks confirmation/dry-run pattern. Parameter descriptions are adequate but could be more prescriptive about format/constraints. No tool annotations visible (readOnlyHint/destructiveHint/idempotentHint) despite clear risk classifications.
Use when the user wants to discover open-source contribution opportunities matched to a developer's skills and interests.
Use when the user wants alternatives similar to a known GitHub login. Similarity uses public repository, language, location, and profile signals and is not a suitability judgment. Example: {"login":"sajeetharan","limit":5}.
Use when the user wants to discover trending developers by language, location, or globally. Trending is based on recent score movements and new entries.
Use when the user names a GitHub login or selects one DevGlobe search result and needs its public profile and contribution evidence. No authentication is required. Example: {"login":"sajeetharan"}.
Use when the user starts with a public GitHub repository and wants relevant indexed developers. Matches public contribution, language, topic, and availability signals without authentication.
Use when the user wants to request a consent-gated introduction to a developer. Requires agent authentication and the developer must have opted in to agent introductions.
Output schemas not documented. LLMs cannot predict response structure (fields, types, pagination) for downstream tool chaining or data extraction.
request_introduction (WRITE tool) lacks confirmation/dry-run pattern. Agents cannot preview introduction requests before sending, risking unintended contact.
No error handling guidance. Tools lack recovery hints (e.g., 'If developer not found, try search_developers with partial name'). Agents cannot self-correct on failures.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 63 | 2025-06-18+ | v2 |
Use when the user wants to find public developers by skill, name, language, location, agent availability, or active opportunity intent. Start discovery here; no authentication is required. Example: {"query":"TypeScript maintainers","location":"Germany","availableForAgents":true,"limit":5}.
Tool annotations missing. Despite clear READ_ONLY and WRITE risk classifications, no readOnlyHint/destructiveHint/idempotentHint metadata visible in schema. Agents cannot infer safety properties.
Parameter descriptions lack format/constraint details. E.g., 'query' accepts 1-200 chars but description does not state this; 'opportunityType' is enum but valid values not listed in description.