3Notch
Related Servers
Alternatives to 3Notch
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenancePreserves continuity between coding agent sessions (e.g., Claude Code and Codex) via local, structured checkpoints, enabling a checkpoint → clear → resume workflow.MIT
- AlicenseAqualityAmaintenanceUniversal session & handoff layer for AI coding agents: shared task, decision, blocker and test state, checkpoints, and deterministic handoff between Claude Code, Codex, OpenCode, Cursor, Cline, pi and omp. Local SQLite, git-aware, 25 tools + 7 resources over stdio or streamable-http.26MIT
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to persist and resume shared working state—tasks, progress, decisions, commands, tests, checkpoints, and handoffs—backed by SQLite while keeping Git authoritative for files and repository state.MIT
- AlicenseNot gradedqualityDmaintenancePersistent, shared memory for Claude across sessions and clients (Code, Desktop, Cowork) — deterministic diff reads, checkpoints, cross-client task handoff, and project-wide search. 100% local and deterministic, no API keys, no LLM summarization.4MIT
- AlicenseBqualityCmaintenancePortable, auditable, local-first MCP memory for MCP-compatible AI agents and coding workflows. It keeps durable project memory outside the model runtime, compresses continuity into smaller working packs, and carries forward operational state so agents can resume with less repetition.2840Apache 2.0
- FlicenseNot gradedqualityCmaintenanceLocal-first deterministic project memory for AI coding agents, with context packs, decisions, gates, risks, scoped claims and explicit checkpoints in project-owned files.-
TDQS
Scored across 23 tools
Tools are grouped into clear workflows: packets, briefs, private seeds, inbox delivery, and diagnostics. A few pairs like create_mark vs create_seed_packet and save_working_state vs create_packet have overlapping intent, but the detailed descriptions provide enough distinguishing conditions.
Nearly all tools follow a snake_case verb_noun pattern such as create_packet, list_briefs, and ack_inbox_delivery, making the set predictable. The main deviation is inbox_init, which uses noun_verb order, and run_doctor is a minor phrase irregularity.
At 23 tools, the server is on the heavy side and falls within the 16-25 range that feels large for agent selection. The tools are individually justified by a broad domain, but several could be consolidated or exposed as subcommands to reduce cognitive load.
The core packet, brief, private-seed, inbox, and health-check lifecycles are well covered, including import, validation, and acknowledgment flows. Minor gaps exist: the default brief can only be read, supersede creation is not exposed even though check_store validates supersede chains, and there is no update/delete for immutable records.