{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_dkq57k6c5zud","handle":"sapience-mcp","url":"https://wellknown.network/agents/sapience-mcp","links":{"self":"https://wellknown.network/agents/sapience-mcp/record.json","html":"https://wellknown.network/agents/sapience-mcp","markdown":"https://wellknown.network/agents/sapience-mcp/record.md","api":"https://wellknown.network/api/v1/agents/sapience-mcp","status":"https://wellknown.network/api/v1/agents/sapience-mcp/status","claim":"https://wellknown.network/agents/sapience-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/sapience-mcp/claim.json","badge":"https://wellknown.network/agents/sapience-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/sapience-mcp/history","tools":"https://wellknown.network/api/v1/agents/sapience-mcp/tools"},"ard":{"identifier":"urn:air::server:sapience-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"sapience-mcp","summary":"Human-like memory and a judgment ledger for AI — an MCP server for Claude Code.","description":"# Sapience\n\n**Human-like memory and a judgment ledger for AI** — an [MCP](https://modelcontextprotocol.io) server for [Claude Code](https://claude.com/claude-code).\n\nAn LLM has *intelligence* — it processes and analyzes brilliantly — but it's amnesiac between sessions and never accumulates *your* experience. Humans win on something else: memory that persists and judgment that gets sharper because we keep track of how our past calls turned out. That faculty — the one that makes *Homo sapiens* more than raw brainpower — is what Sapience adds to your AI.\n\nTwo halves:\n\n- **A human-like memory** — episodic and semantic memories, ranked by importance, consolidated over time into durable patterns. Not RAG over a scratch file.\n- **A judgment ledger** — log a prediction with a probability, resolve it against what actually happened, and get a real calibration read (Brier score, reliability by confidence band, a bias map) so you can see where your judgment is systematically off.\n\n> Sapience gives *one user's* AI a compounding memory + judgment loop. It is not a claim to reproduce human cognition — it's the missing feedback loop that lets an intelligence learn from experience.\n\n## The judgment ledger\n\nThis is the part you won't find in other memory tools. Every \"AI memory\" remembers what you said; Sapience keeps score of whether you were *right*.\n\n1. **Log** a forward-looking call with a probability (0–1) and — crucially — the *reasoning and conditions as they were at the time*. Most retrospectives rewrite history; this preserves the contemporaneous evidence.\n2. **Resolve** it when the outcome is known (right / partial / wrong).\n3. **Calibrate.** Sapience computes a **Brier score** against a base-rate baseline, breaks accuracy down by confidence band, and flags over/under-confidence. A Claude-written narrative sits *on top of* the numbers — never instead of them.\n\n**Honesty by design:** below a sample threshold (20 binary-scored resolutions by default — partial resolutions don…","publisher":{"name":"Allen Chen","url":null},"homepage":"https://github.com/allenc84/sapience","repository":"https://github.com/allenc84/sapience","version":"0.2.1","license":null,"protocols":["mcp"],"tags":["mcp","claude","ai-memory","judgment-ledger","calibration","llm"],"pricing":null,"endpoints":[{"url":"pypi:sapience-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"derived"},{"slug":"finance.accounting","name":"Accounting","confidence":1,"provenance":"derived"}],"categories":["finance","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"sapience-mcp","registry":"pypi","observedAt":"2026-10-22T19:28:01.610Z","publishedAt":"2026-10-14T20:52:10.101781Z","latestVersion":"0.2.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"sapience-mcp","url":"https://pypi.org/project/sapience-mcp/","firstSeenAt":"2026-09-10T11:27:52.457Z","fetchedAt":"2026-10-22T19:26:42.895Z","normalizedAt":"2026-10-22T19:26:42.895Z"}]},"firstSeenAt":"2026-09-10T11:27:52.457Z","updatedAt":"2026-10-22T19:28:01.610Z"}