CommitLore
Related Servers
Alternatives to CommitLore
No user-submitted related servers found.
Related Servers
- AlicenseAqualityAmaintenanceLocal-first memory layer for AI coding agents — captures issues, attempts, fixes, and decisions, and warns at git commit before you repeat a mistake.17799MIT
- AlicenseAqualityBmaintenanceLocal-first project memory for AI coding agents. Records failed attempts, fragile files, and decisions per repo, and warns the agent via hooks before it repeats a recorded mistake.650 npmMIT

robo-cortexofficial
AlicenseAqualityAmaintenanceProvides a git-aware knowledge base for AI coding agents to store and retrieve memories anchored to code changes, with automatic staleness detection.81MIT- AlicenseAqualityAmaintenanceGit-native long-term memory for AI agents: your markdown files are the source of truth, the search index is a disposable projection rebuilt from git, and every memory the agent writes is a reviewable git commit. Served over one OAuth-secured MCP endpoint with hybrid lexical+semantic recall and a gated, git-first commit_note write tool.78AGPL 3.0
- FlicenseNot gradedqualityCmaintenanceAuto-captured, auto-recalled, path-scoped memory for AI coding agents and teams.2-
- AlicenseAqualityAmaintenanceSelf-hosted decision memory for AI coding agents. Captures decisions with the alternatives you rejected, and warns before an agent re-proposes a rejected approach.481Apache 2.0
TDQS
Scored across 8 tools
commitlore_before_change and commitlore_guard have identical descriptions and appear to be the same tool under different names, creating a serious selection ambiguity. The remaining tools are distinct enough, but this duplicate pair prevents an agent from reliably choosing between them.
All names share the commitlore_ prefix and use snake_case, which provides some coherence. However, the suffixes mix patterns: verb_noun for capture tools, bare verbs like query, adjectives like stale, and descriptive phrases like before_change and runtime_identity.
Eight tools is well within the ideal range for a focused domain. The count covers runtime introspection, querying, advisory checking, and the prepare-verify-stage capture lifecycle without feeling bloated.
The main workflow is well covered: query records, check proposals, prepare/verify/stage captures, and identify stale records. The most notable gap is the lack of an explicit cancel or discard path for a prepared capture transaction, though this may be a minor operational concern rather than a critical dead end.