Long-term memory for AI-coded codebases. A local MCP server that captures the why behind every change agents make, then reads it back: with prior_attempts, the agent checks 'was this tried here before, and how did it turn out?' before it edits.
How to install selvedge?
masondelan/selvedge
$claude plugin marketplace add masondelan/selvedgeInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install selvedge by running `claude plugin marketplace add masondelan/selvedge`, then use it for the current task and follow its documentation at https://github.com/masondelan/selvedge.
Related
6 picksType
- skillsMatt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.Jul 2026
- ponytailLazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.Jul 2026
- understand-anythingAI-powered codebase understanding — analyze, visualize, and explain any projectJul 2026
- open-code-reviewOpen-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.Jul 2026
- improvePoint it at a codebase and it figures out what's worth doing — bugs, perf, tech debt, what to build next — then writes plans any agent can execute. It can hand the work to a cheaper model and review the result. It never edits your code.Jun 2026
- plannotatorAnnotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.Jul 2026
