indifferentketchup
c935687725
Drop 9 batch proposals that are superseded by the boocode-lift-analysis (boocontext-audit, conductor upgrades, self-healing/verify-gate skills): add-3tier-memory, import-llm-evaluator, import-pregel-engine, plugin-platform, conductor-evolution, code-intelligence-upgrade, dev-workflow, ui-overhaul, agent-reliability. Delete 11 stub archive files (49-66B each, 'Status: Shipped. Archived.' only) that provide zero documentation value over the existing CHANGELOG.md + git tags.
2.7 KiB
2.7 KiB
Why
Current AI agents lack structured, durable memory beyond the immediate context window. Conversations are stateless, preferences are forgotten, and long-term learning is nonexistent. Three OSS repos (LangMem, DeerFlow, CowAgent) demonstrate production patterns for agent memory — but no unified, portable engine exists that combines short-term context management, long-term semantic memory, tiered consolidation, and hybrid retrieval. This change builds that engine by extracting and adapting the best patterns from all three.
What Changes
- New
memory-engine/module in the codebase providing a unified memory & context API - Short-term context summarization — token-budget-aware conversation windowing (LangMem pattern)
- Long-term semantic memory — LLM-extracted facts stored with optional vector embeddings (LangMem/DeerFlow hybrid)
- Tiered memory architecture — Context tier (ephemeral session) → Daily tier (summarized records) → Core tier (distilled long-term) (CowAgent pattern)
- Hybrid search — Keyword (FTS5) + Vector (cosine similarity on embeddings) with weighted merge (CowAgent pattern)
- Background consolidation — Debounced, async memory extraction pipeline (DeerFlow queue + LangMem ReflectionExecutor)
- Deep Dream distillation — Periodic overnight LLM consolidation of daily records into core memory (CowAgent pattern)
- Memory tools for agents —
manage_memoryandsearch_memorytool interfaces (LangMem pattern)
Capabilities
New Capabilities
short-term-context: Token-budget window management, conversation summarization, and context trimming for LLM interactionslong-term-memory: Persistent fact extraction, storage, and retrieval with Pydantic-typed schemastiered-consolidation: Three-tier memory pipeline (context→daily→core) with promotion rules and Deep Dream distillationhybrid-search: Combined keyword (FTS5) + vector (embedding cosine similarity) search with weighted scoring and temporal decaymemory-tools:manage_memory(CRUD) andsearch_memory(semantic query) tools for agent integrationbackground-processing: Debounced async memory update queue with thread-pool execution
Modified Capabilities
Impact
- New
memory-engine/directory tree (no existing code modified) - Dependencies:
sqlite3(stdlib),numpy(optional, for vector search),pydantic(schemas),tiktoken(token counting) - LLM provider integration via abstract
ChatModelinterface (not coupled to any provider) - Embedding provider integration via abstract
EmbeddingProviderinterface (supports OpenAI, local models) - Agent integration via simple tool interface (not coupled to any agent framework)