MCP Server and AI Agent Skills for OpenGraphMemory
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"ogm-mcp-skills","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# ogm-mcp-skills MCP stdio server and AI Agent Skills from Claude Code, OpenCode, Antigravity, and Hermes to OpenGraphMemory and the Codebase Knowledge Graph. The MCP server uses authenticated OpenGraphMemory REST APIs only. It is stateless: no local database, session mapping, direct PostgreSQL, Neo4j, or object-store access. ## Status Alpha. PyPI releases are published from GitHub Actions on `v*` tags. Source install is also supported for development. ## Tools - `ogm_health` - `ogm_list_datasets` - `ogm_search_entities` - `ogm_get_entity` - `ogm_get_neighbors` - `ogm_find_path` - `ogm_get_subgraph` - `ogm_get_graph` - `ogm_get_evidence` - `ogm_get_relation_evidence` - `ogm_upload_document` - `ogm_memory_list_episodes` - `ogm_memory_get_episode` - `ogm_memory_search` - `ogm_memory_create_episode` - `ogm_memory_append_attempt` - `ogm_memory_record_outcome` - `ogm_memory_feedback_episode` - `ogm_memory_supersede_episode` - `ogm_memory_feedback_pattern` - `ogm_memory_supersede_pattern` - `ogm_search_code_symbols` - `ogm_get_code_call_graph` - `ogm_get_code_chunks` - `ogm_recall_code_memory` - `ogm_record_code_fix` - `ogm_sync_code_file` Read tools inspect PostgreSQL-authoritative graph and Agent Memory data. Agent Memory results are historical claims: inspect recorded evidence and verifiers before relying on them. `personal-safe` permits reviewed document upload, additive Agent Memory records, and code sync; `memory-curator` additionally permits memory feedback and supersession. No delete, admin, project-create, relation-review, analytics-refresh, semantic-retrieval, or automatic conversation-ingestion tools exist. ## Install Install from PyPI with `uv`: ```bash uv tool install ogm-mcp-skills ``` Or run without installing: ```bash uvx ogm-mcp-skills==0.2.2 --version ### Automated 1-Command Setup Automatically copy `SKILL.md` and merge MCP server configuration into your installed agent harness (Antigravity, Gemini CLI, Claude Desktop, Cursor, etc.): ```ba…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.