Results for embedded_record

Self-Optimizing Neural Architecture - Runtime-adaptive learning for LLM routers with two-tier LoRA, EWC++, and ReasoningBank

Embedding providers (local + cloud) for Anamnesis. Local default: fastembed-rs.

Anamnesis adapter for Claude Code (~/.claude/projects)

Anamnesis adapter for OpenAI Codex (~/.codex/sessions, ~/.codex/conversations)

Generic MCP adapter — import memory from any MCP-aware server

Anamnesis adapter for ghast (Electron AI companion) — reads prompts/, resources/bundled-skills/, and flags the encrypted user-profile DB

Anamnesis adapter for Hermes Agent (Nous Research) — reads ~/.hermes/{MEMORY,USER}.md + the SQLite session store

Anamnesis adapter for Letta (formerly MemGPT) — reads the self-hosted ~/.letta/letta.db SQLite store

Anamnesis adapter for mem0 (self-hosted SQLite or cloud API)

Anamnesis adapter for Memary (kingjulio8238/Memary) — reads the JSON cache files (memory_stream, entity_knowledge_store, past_chat, persona)

Anamnesis adapter for Memori (MemoriLabs/Memori) — reads SQLite-backed entity facts, process attributes, conversation messages, conversation summaries, and KG triples

Anamnesis adapter for MemOS (MemTensor/MemOS) — reads dumped MemCube directories (textual_memory.json) under ~/.memos/ or a user-supplied root