FlowState by DialectForge
OfficialRelated Servers
Alternatives to FlowState by DialectForge
No user-submitted related servers found.
Related Servers
AlicenseNot gradedqualityAmaintenanceGives AI apps a shared, plain-folder memory on your own machine, so whatever you tell one model the others can read, and you can inspect, review and undo every change they make. Memory stays portable across vendors, models and account changes instead of living on a provider's servers.7Apache 2.0- AlicenseNot gradedqualityBmaintenanceLocal-first, multi-user shared memory for AI agents with semantic search, offline support, and team synchronization.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding agents to share a local-first, versioned memory of decisions, conventions, tasks, conflicts, and handoffs over MCP and REST.1 npmMIT
- AlicenseAqualityAmaintenanceEnables multiple AI agents on one machine to write, search, fetch, link, and give feedback on a shared local store of Markdown-backed facts, preferences, and conventions that persists across sessions. Memories gain confidence as different hosts confirm their use and can be distilled into denser ones, so agents stop re-discovering the same context.5888 PyPI1MIT

Lians Agent Memoryofficial
AlicenseAqualityCmaintenanceLocal-first bitemporal memory for AI agents with deterministic supersession, point-in-time recall, erasure proofs, and tamper-evident audit history.916Apache 2.0- AlicenseAqualityBmaintenanceLocal-first memory engine for AI-agent teams: private/team/project ACL, associative recall, and federated sync across nodes. One SQLite file, no LLM required.127Apache 2.0
TDQS
Scored across 35 tools
Several tools overlap meaningfully: log_work(kind=change/learning/problem/todo) duplicates log_change, log_learning, problem, and todo; ask/search/get_learnings/get_recent_changes all retrieve records; and start_here vs get_context both return session context. Descriptions do help an agent pick correctly, but boundaries are genuinely blurred in the write path.
Two clear conventions coexist: verb_noun tools (create_project, log_learning, review_approve, get_recent_changes) and bare resource nouns that dispatch via an action parameter (todo, session, file, git, variable, method, rules, problem). Each family is internally predictable, but the split is roughly half-and-half rather than a minor deviation.
35 tools is above the 25+ heavy threshold for a project-memory server. While many consolidate multiple operations behind an action parameter, the surface is still large and the count alone makes selection cost high.
Coverage is broad and coherent: projects, components, learnings, changes, problems, attempts, todos, sessions, files, git, variables, methods, links, review workflow, rules, history/undo, import, and cleanup. The main gap is explicit deletion for projects, components, learnings, and changes (partially mitigated by history undo), which agents can work around.