{"id":"roampal-ai-roampal-core","name":"roampal-core","homepage":"https://roampal.ai","repo_url":"https://github.com/roampal-ai/roampal-core","category":"ai-ml","subcategories":[],"tags":["ai-memory","mcp","persistent-memory","semantic-search","python","fastapi","vector-database","developer-tools"],"what_it_does":"roampal-core is a Python MCP server plus a local HTTP hook/service that injects relevant long-term and outcome-scored memory into AI coding assistants (Claude Code and OpenCode). It also scores prior exchanges, promotes good advice, demotes bad advice, and supports ingesting reference documents for retrieval via semantic search across multiple memory collections.","use_cases":["Persistent memory for AI coding assistants across editor sessions","Capturing and learning from outcomes of prior advice to improve future responses","Semantic retrieval over ingested documents (books) and historical conversations","Maintaining durable coding preferences and identity facts (memory_bank)","Automated context injection into Claude Code (hooks) and OpenCode (plugin)"],"not_for":["Use as a public-facing multi-tenant SaaS API without additional hardening","Environments that cannot run a local HTTP server / local background scoring sidecar","High-assurance environments requiring formally documented security guarantees for all endpoints"],"best_when":"You want fully local/private persistent memory for AI coding assistants and can run a small local service (and optional sidecar scoring model) on your machine.","avoid_when":"You require strict enterprise-grade authz/authn, audit logging, and documented data handling controls for remote or multi-user deployments.","alternatives":["Mem0 (persistent memory with RAG; often more API-centric)","Vector DB + reranking pipeline you control (e.g., Chroma + cross-encoder reranking)","Static project rules / prompts (e.g., .cursorrules/CLAUDE.md) without outcome learning","Generic MCP memory servers (if you already have scoring/promotions logic elsewhere)"],"af_score":54.0,"security_score":29.2,"reliability_score":41.2,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T15:26:06.627025+00:00","interface":{"has_rest_api":true,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":[],"oauth":false,"scopes":false,"notes":"No explicit authentication mechanism is described in the README for the local HTTP server (example health check uses localhost). The MCP tools appear to be consumed by the host coding assistants configured during roampal init."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Described as completely free and open source; costs may arise from using remote models for scoring if local models are not configured."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":54.0,"security_score":29.2,"reliability_score":41.2,"mcp_server_quality":65.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":90.0,"rate_limit_clarity":5.0,"tls_enforcement":20.0,"auth_strength":30.0,"scope_granularity":0.0,"dependency_hygiene":65.0,"secret_handling":40.0,"security_notes":"The README describes a local HTTP server with a localhost health check but does not document TLS requirements, authentication/authorization, or secret-handling/logging behavior for HTTP/MCP endpoints. Scoring models may be remote (Zen free models by default per README), which can affect data exposure depending on configuration.","uptime_documented":20.0,"version_stability":35.0,"breaking_changes_history":40.0,"error_recovery":70.0,"idempotency_support":"false","idempotency_notes":"No explicit idempotency semantics are documented for MCP tools or HTTP endpoints; operations like add/update/delete memories may be non-idempotent without client-side deduplication.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["OpenCode scoring uses an independent sidecar; if unavailable, users must configure it (and the MCP tool score_memories is not registered on OpenCode).","The system depends on the local HTTP server being reachable at the configured port (27182 in examples).","If Claude Code hooks are not loaded, context injection may fail until Claude Code is restarted."]}}