vnem

Better context for coding LLMs.

vnem adds current tools, MCPs, skills, evals, prompt patterns, and upgrade paths to your repo so your agent can review the stack before it codes.

from project root
curl -fsSL https://vnem.ai/install.tgz | tar -xz

Sharper stack reviews. Better tool choices. Cleaner diffs.

what the agent gets

Current agent tooling

Searchable guidance for MCP servers, skills, agent frameworks, evals, memory, identity, payments, and workflow patterns.

Repo-aware review protocol

The agent inspects manifests and configs first, then separates stale or risky choices from better current options.

Prompt forge

Prompt drafts get rewritten with goal, scope, constraints, approval boundaries, verification, and final reporting.

inside the pack

Five local files. Better agent judgment.

  • .vnem/AGENTS.mdhow the agent should read and report
  • .vnem/search-index.jsontools, MCPs, scores, freshness, risk flags
  • .vnem/best-practices.mdcurrent stack guidance by project area
  • .vnem/prompt-engineering.mdprompt enhancement protocol
  • .vnem/prompt-patterns.jsonmachine-readable task patterns