Local-first OSS DB/workspace where Claude Code/Codex/Cursor share durable records, docs, skills, and apps—writes that matter go through human review; Skill, MCP, OpenAPI, and ACP connections keep agents stateless and work durable.
Anthropic adds Dreaming (research preview: cross-session memory curation; Harvey saw ~6× completion), Outcomes (grader rubric + iterate; +~10 pts on hard tasks), and lead/specialist multiagent orchestration with webhooks—so Managed Agents can self-improve, self-grade, and parallelize without constant human steering.
OSS (AGPL): index a folder of Markdown notes into local SQLite, then expose search/recall/remember tools over MCP so Claude Code/Codex reuse decisions across sessions; hosted option at renor.cloud.
Single Rust binary indexes calls/imports with tree-sitter, stores project/session memory in one SQLite file, and serves cited line-anchored excerpts over MCP—setup wires Claude Code/Codex/Cursor; reported 3–22× faster extracts vs Graphify on 13 codebases.
Memanto 0.2.28 ships a Python client so any agent gets persistent typed memory with one import: remember()/recall()/answer()/extract() plus point-in-time recall_as_of and recall_changed_since. Cloud (free tier) or on-prem Docker+Ollama; no vector store to provision. Loop pattern: recall before your LLM call, extract only the user’s turn after—connects to Claude Code/Cursor/Codex via memanto connect.
Meta AI Research (Oct 12) ships Muse Wonder and Muse Wonder Full for long agent workflows: Active Memory carries user context across sessions; Active Focus stays on goals with check-ins before high-impact actions; demos cover browser/app work (run planning, custom gifts, seating charts) plus frontier coding. Available via Meta Model API and Muse Code (Wonder Full for Muse Code subscribers); will power Muse experiences for subscribers first. Soft-dupes Muse Spark Open already on-site—this card is the Wonder series agent release.