The request names no specific product, and "convention-learner" most closely matches tooling that learns and enforces coding conventions from a codebase. Among the candidates, sources 1 and 5 show agent and workflow features that learn or record conventions and lessons (GitHub's /remember and memory-merger actions, Cursor's continual-learning action), while 9 and 7 are general platforms that do not show convention learning. Nothing in the sources confirms a tool whose sole purpose is lea
A question back: Do you mean a tool that infers coding conventions from an existing codebase (for example style or naming rules), or one that learns from your agent's past lessons and corrections? The answer changes w
- 1
GitHubgithub.comverified and signed
Its /remember action turns lessons learned into domain-organized memory instructions, and memory-merger merges mature lessons into instruction files 11.
official:CLI · github-mcp-serverskill · add-community-extensionskill · git-commitskill · acquire-codebase-knowledge+2,563 community tools built for it
for agents: conventional-commit · remember · memory-merger
- 2
Cursorcursor.comverified and signed
Its continual-learning action orchestrates learning by delegating transcript mining and AGENTS.md updates to agents-memory-updater 15.
+174 community tools built for it
for agents: continual-learning · create-learning-path · run-learning-retrospective
Sources
- 1GitHub · Change is constant. GitHub keeps you ahead. · GitHub · GitHubgithub.com · read 2026-10-29
- 5AI Coding Agent for Building Ambitious Software | Cursorcursor.com · read 2026-10-29
- 7SentenceTransformers Documentation — Sentence Transformers documentationsbert.net · read 2026-10-29
- 9Ollama · Run AI models locally and in the cloudollama.com · read 2026-10-29
- 11conventional-commit: declares "conventional-commit" (the record we read and signed)unfragile.ai · read 2026-10-24
- 15continual-learning: declares "continual-learning" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
conventional-commit · conventional-commit verified and signed
Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, examples, and validation.
python · fastcore verified and signed
· Langchain Google website read, tools not yet checked
LangChain enables every company to own their intelligence. Control, govern, and compound intelligence with an open agent engineering platform.
create-design-system-rules · create-design-system-rules verified and signed
Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma
continual-learning · continual-learning verified and signed
Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.
key-value-store · redis verified and signed
learning · sentence-transformers verified and signed
learning · torch verified and signed
· Ollama website read, tools not yet checked
Ollama is the easiest way to run and build with open AI models locally or in the cloud on macOS, Windows, and Linux.
rust-learner · rust-learner verified and signed
Use when asking about Rust versions or crate info. Keywords: latest version, what's new, changelog, Rust 1.x, Rust release, stable, nightly, crate info, crates.io, lib.rs, docs.rs, API documentation, crate features, dependencies, which crate, what version, Rust edition, edition 2021, edition 2024, c
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.