{"name":"io.github.rastogivaibhav/llm-kosh","slug":"rastogivaibhav-llm-kosh","title":null,"description":"Local-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.","url":"https://mcp.market/server/rastogivaibhav-llm-kosh","rating":null,"grade":"A","score":92,"certified":false,"status":"active","category":"data","tags":["data","ai"],"presence":{"score":25,"stars":1,"forks":1,"downloads_week":27,"last_push_at":"2026-09-14T00:36:59.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"pypi","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/rastogivaibhav/llm-kosh","website":null,"version":"2.1.3","remotes":[],"packages":[{"registryType":"pypi","identifier":"llm-kosh","version":"2.1.3","transport":{"type":"stdio"},"environmentVariables":[{"description":"Path to the local folder llm-kosh should use as its memory cartridge root.","isRequired":true,"format":"filepath","name":"CARTRIDGE_WORKSPACE"}]}],"tools":[{"name":"apply_intake_proposal","description":"Directly applies an intake proposal batch to the live memory.","write_action":false,"price_micros":0,"input_schema":null},{"name":"create_private_context_pack","description":"Creates a highly focused context pack for a specific task. Includes private and sensitive information.","write_action":true,"price_micros":0,"input_schema":null},{"name":"get_cartridge_memory_map","description":"Returns a structural map of the knowledge base projects and active concepts.","write_action":false,"price_micros":0,"input_schema":null},{"name":"get_daemon_status","description":"Verifies the cryptographic ledger of the Cartridge.","write_action":false,"price_micros":0,"input_schema":null},{"name":"get_project_context","description":"Fetches all context and active decisions for a specific project.","write_action":false,"price_micros":0,"input_schema":null},{"name":"intake_convert_file","description":"Converts a local file (e.g. PDF, DOCX, XLSX, PPTX, PNG, WAV) to structured markdown using the MarkItDown converter and ingests it into the cartridge.","write_action":false,"price_micros":0,"input_schema":null},{"name":"list_intake","description":"Lists the current items pending in the intake queue.","write_action":false,"price_micros":0,"input_schema":null},{"name":"reasoning_critique","description":"Run the Lyapunov critic on a specific list of fact IDs. Returns stability score, status, and per-dimension breakdown.","write_action":true,"price_micros":0,"input_schema":null},{"name":"reasoning_explore","description":"Enumerate all causal paths between two known facts. Returns the fiber bundle for that specific pair.","write_action":false,"price_micros":0,"input_schema":null},{"name":"reasoning_ingest","description":"Add a new fact to the Temporal Causal Reasoning Graph. documented_at and valid_from are ISO 8601 datetime strings. causal_edges: JSON array of {\"target_id\": str, \"edge_type\": str, \"confidence\": float}. Returns the new fact_id.","write_action":false,"price_micros":0,"input_schema":null},{"name":"reasoning_query","description":"Query the Temporal Causal Reasoning Graph. By default returns a human-readable causal narrative (narrative=True). Set narrative=False to get raw JSON with full fiber bundle details. temporal_context: ISO 8601 datetime or Unix timestamp string (omit for now).","write_action":false,"price_micros":0,"input_schema":null},{"name":"search_memory","description":"Search the Cartridge Knowledge Base for memories, decisions, and files.","write_action":false,"price_micros":0,"input_schema":null},{"name":"submit_memory_receipt","description":"Submits a MEMORY_RECEIPT.md formatted string to the intake queue. Does not apply it directly; it must be reviewed and applied.","write_action":true,"price_micros":0,"input_schema":null}],"scan":{"score":92,"grade":"A","scanned_at":"2026-09-26T16:36:36.761Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-26T16:36:36.660Z","components":{"code":{"score":25,"max":25,"notes":["83 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":15,"max":15,"notes":["last push 13 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[],"inputs":{"packages":[{"registryType":"pypi","identifier":"llm-kosh","version":"2.1.3","found":true,"weeklyDownloads":27,"license":"MIT","dependencyCount":13,"publishedAt":"2026-06-23T15:44:35.746979Z","repositoryUrl":"https://github.com/rastogivaibhav/llm-kosh"}],"repo":{"found":true,"owner":"rastogivaibhav","repo":"llm-kosh","archived":false,"pushedAt":"2026-09-14T00:36:59Z","stars":1,"forks":1,"openIssues":0,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/44193373?v=4","ownerCreatedAt":"2018-10-16T08:41:18Z","license":"MIT"},"icon":{"url":"https://avatars.githubusercontent.com/u/44193373?v=4&s=128","source":"github"},"presence":{"stars":1,"forks":1,"downloadsWeek":27,"license":"MIT","lastPushAt":"2026-09-14T00:36:59.000Z","score":25}}}},"grade_history":[],"reviews":[]}