{"id":"allenmaxi-contextgraph","name":"ContextGraph","af_score":51.0,"security_score":54.8,"reliability_score":27.5,"what_it_does":"ContextGraph is a governed shared-memory layer for multi-agent systems. It stores agent claims with provenance/freshness/trust metadata, enforces access control at retrieval time, and compiles token-budgeted “context packs” (optionally explainable) for each agent’s permissions. It provides a Python SDK, CLI/dashboard, an HTTP REST API, and an MCP server/tool integration, with optional Anthropic Claude Memory Tool adapter support and a Neo4j-backed self-hosted beta path.","best_when":"You run multiple agents (and/or organizations) that must share knowledge safely, with auditable provenance, freshness/trust controls, and token-budgeted context assembly per caller permissions.","avoid_when":"You only need lightweight retrieval and cannot justify governance overhead (provenance, reviews, sentinel verdicts, explainability, persistence of context packs).","last_evaluated":"2026-03-30T15:38:33.611372+00:00","has_mcp":true,"has_api":true,"auth_methods":["Authentication/authorization details not explicitly provided in README content provided"],"has_free_tier":false,"known_gotchas":["Governed retrieval behavior depends on permissions (agent/org visibility) and claim gates (freshness/trust/sentinels/payment locks); agents may see empty/locked claims if authorization or gates don’t allow access.","Compiled context packs are persisted and retrievable; agents should use pack_id correctly rather than assuming recall/compile are stateless.","No explicit retry/idempotency semantics were documented in provided README content; agents may need to implement conservative retries for POST operations."],"error_quality":0.0}