katolikov/kanerva
Long-term memory for coding agents: Claude Code, Codex, OpenCode, OpenClaw, Copilot, Cursor and more. Local SQLite, no LLM calls, hard token budget. Your agent remembers decisions, commands and fixes across sessions, and gets only what the
field: AI / ML
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~5.1k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code
$ claude mcp add kanerva -- {{RUN}} mcp MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add kanerva -- {{RUN}} mcp $ npx degit katolikov/kanerva/plugins/claude-code/skills/forget .claude/skills/forget $ npx degit katolikov/kanerva/plugins/claude-code/skills/memory .claude/skills/memory $ npx degit katolikov/kanerva/plugins/claude-code/skills/remember .claude/skills/remember
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (2)
| server | source | est. tokens |
|---|---|---|
| memory | local / custom | 2.5k |
| {{run}} · "kanerva" | binary | 2.5k |
Skills (3)
Similar rigs
MyMemoAI/openmymemo
Your AI memory as a local folder you own. Claude, Codex, Cursor and any MCP app share it; you see every change and can undo it.
Pragmatist 7.5k tok · · Q3
Lexxes-Projects/obey
Makes Claude actually follow your rules. Save rules with natural language, enforce them with hooks, remember them across sessions.
Minimalist 579 tok · · Q0
kitfunso/hippo-memory
Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps
Minimalist 1.3k tok · · Q8
Digital-Process-Tools/claude-remember
Persistent memory for Claude Code — identity, context, and continuity across sessions
Minimalist 545 tok · · Q3