Topic
Source-linked workflows that name Memory. Part of the AI agent use cases on UsecaseBoard, or browse all use cases.
A builder shipped a Karpathy-inspired shared-spine memory for Grok Bot—one wiki, permanent bidirectional links, short/medium/long-term as tags (never copies), with a nightly tidy job.
Product Hunt’s Cronloop lets you describe a recurring job in Markdown, pick Codex or Claude Code, connect tools, and run agents on a loop with durable memory that can self-improve each run.
A Tesla driver built Drivr—a single-purpose Grok Bot that listens while they think out loud on the road and files the rant into a lasting memory doc instead of a general chat.
An Indie Hackers post breaks down the architecture for an AI secretary that actually keeps context: session vs short-term task vs long-term preference layers so birthday/contact and calendar commitments survive across chats.
A builder whose Grok Bot team kept remembering different versions of the rules moved one Evernote handbook as the single source of truth every bot reads—plus a copy-paste folder tree for the setup.
Builder moved bot memory into an Obsidian vault so Grok Bot, Meta Muse, ChatGPT Dots, and Hermes bots all reuse the same projects and preferences instead of re-teaching each agent from scratch.
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.
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.
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.