A
licenseNot graded
qualityD
maintenancePreserves continuity between coding agent sessions (e.g., Claude Code and Codex) via local, structured checkpoints, enabling a checkpoint → clear → resume workflow.
MIT
task-checkpoint
by qddfxp
Related Servers
Alternatives to task-checkpoint
No user-submitted related servers found.
Related Servers
contextportofficial
AlicenseNot gradedqualityBmaintenanceEnables AI coding sessions to save task progress, decisions, next steps, and verification evidence as local snapshots, then resume with file-change and freshness checks. It supports evidence-aware handoffs without running tests or calling model APIs.MIT- AlicenseNot gradedqualityNot gradedmaintenanceEnables agents to persist and resume long-horizon tasks using cryptographic event-sourced checkpoints, idempotency deduplication, scheduled heartbeats, pause/resume tokens, and fail-safe recovery.MIT
- AlicenseAqualityBmaintenanceEnables coding agents to register tasks, report progress, save checkpoints, and report interruptions so an independent watchdog can automatically resume interrupted work from the same session or a saved checkpoint.794 npmMIT
genpark-long-horizonofficial
AlicenseNot gradedqualityBmaintenanceEnables long-horizon autonomous task checkpointing and resumption through cryptographic event-sourced state persistence, idempotency key deduplication, timeout heartbeats, human-in-the-loop pause/resume tokens, and fail-safe recovery.7MIT- AlicenseAqualityBmaintenanceLocal-first working-state checkpoints and portable handoff packets for AI coding agents. Continuation checkpoints recover Claude Code sessions after rate limits, crashes, and compaction; packets hand tasks across tools, repos, and machines — Markdown on disk, no cloud, no telemetry.2324 npm4MIT
TDQS
A3.7/5.0
Scored across 10 tools
Disambiguation4/5
Most tools target clearly distinct operations (init, import, export, compress, switch, restore). Minor overlap exists between tc_capture (record live changes) and tc_save (persist a step), and between tc_resume (status) and tc_show (list steps), but the two-layer model (task layer vs change layer) largely keeps them separable.
Naming Consistency5/5
Every tool uses the same tc_ prefix followed by a single concise verb (init, import, capture, compress, export, restore, resume, save, show, switch). The pattern is perfectly predictable throughout.
Tool Count5/5
Ten tools is well-scoped for a task-checkpoint lifecycle. Each tool maps to a distinct lifecycle concern (create, persist, capture, resume, inspect, restore, clean, hand off) with no filler.
Completeness4/5
The lifecycle is broadly covered: create, save/close, capture, status, list, switch, restore, compress, and export/import handoff. Closing a task is folded into tc_save (close=true) rather than a dedicated tool, and there is no explicit task deletion, but these are minor workable gaps.
Maintenance
ActivitySlowing
ResponsivenessNo recent community issues