{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_7hkyrs2z7mtt","handle":"aegisdb-mcp","url":"https://wellknown.network/agents/aegisdb-mcp","links":{"self":"https://wellknown.network/agents/aegisdb-mcp/record.json","html":"https://wellknown.network/agents/aegisdb-mcp","markdown":"https://wellknown.network/agents/aegisdb-mcp/record.md","api":"https://wellknown.network/api/v1/agents/aegisdb-mcp","status":"https://wellknown.network/api/v1/agents/aegisdb-mcp/status","claim":"https://wellknown.network/agents/aegisdb-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/aegisdb-mcp/claim.json","badge":"https://wellknown.network/agents/aegisdb-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:aegisdb-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"aegisdb-mcp","summary":"Integrate AegisDB as persistent memory for Claude Code (MCP server + hooks)","description":"# AegisDB ↔ Claude Code Memory Integration\n\nMake [AegisDB](https://github.com/d4n-larsson/aegisdb) the **persistent long-term memory** of Claude\nCode. The agent gets memory **tools** (save/search/get/update/relate) via an MCP\nserver, plus automatic **recall** and **capture** via hooks — so knowledge learned\nin one session (decisions, conventions, fixes, preferences) is available in later\nones without the user re-explaining it. Each project keeps its own isolated memory.\n\n## How it works\n\n```\nClaude Code ──(MCP stdio)──▶ aegis_mcp.server ──┐\nClaude Code ──(hooks)──────▶ recall/capture ────┼──▶ AegisDB (NDJSON/TCP)\n                             embeddings ─────────┘\n```\n\n- **MCP tools** (`mcp__memory__memory_save`, `_search`, `_get`, `_update`, `_relate`) —\n  explicit, model-driven memory.\n- **`UserPromptSubmit` hook** — automatic recall: injects relevant memories into\n  context before each turn, best-effort under a time budget.\n- **`SessionEnd` hook** — automatic capture: persists salient session outcomes.\n- **Embeddings** — pluggable provider (Voyage / local / none) turns text into\n  vectors for semantic recall; the integration never asks the agent for vectors.\n\nAll logic lives in dependency-free modules under `aegis_mcp/`; only the MCP server\nentry point needs the `mcp` SDK. Memory is always best-effort: if AegisDB is down,\nthe agent stays fully usable.\n\n## Why it saves tokens\n\nLong context is the real cost driver, and this integration keeps durable\nknowledge **out** of the window — feeding back only what's relevant per prompt —\nso you spend tokens on the work, not on re-establishing context.\n\n- **Recall instead of re-explaining.** Stack, conventions, decisions, and gotchas\n  learned earlier are injected automatically, so you stop re-pasting them every\n  session and the model stops re-deriving them.\n- **A relevant slice, not a dump.** Recall ranks by similarity × importance ×\n  confidence and injects only the top matches — capped by `AEGIS_RECALL_TOP_K`,\n  filtered…","publisher":null,"homepage":"https://github.com/d4n-larsson/aegisdb","repository":"https://github.com/d4n-larsson/aegisdb","version":"0.9.4","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:aegisdb-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"}},"derived":{"capabilities":[{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"derived"},{"slug":"data.vector-search","name":"Vector Search","confidence":0.825,"provenance":"derived"}],"categories":["data","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":"aegisdb-mcp","registry":"pypi","observedAt":"2026-09-09T08:22:24.302Z","publishedAt":"2026-08-27T05:33:08.774829Z","latestVersion":"0.9.4"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"aegisdb-mcp","url":"https://pypi.org/project/aegisdb-mcp/","firstSeenAt":"2026-09-09T08:20:36.799Z","fetchedAt":"2026-09-09T08:20:36.799Z","normalizedAt":"2026-09-09T08:20:36.799Z"}]},"firstSeenAt":"2026-09-09T08:20:36.799Z","updatedAt":"2026-09-09T08:22:24.302Z"}