agentrigs
+ submit rig
~ / rigs / NickCirv / engram

NickCirv/engram

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via npm + OpenVSX + Anthropic plugin directory. 89% measured token reduction. Local SQLite, zero cloud,

↗ GitHub ★ 142 apache-2.0 updated 17d ago project Claude CodeCodexCursor Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~3.5k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add engram -- engram-serve ${CLAUDE_PROJECT_DIR}

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 engram -- engram-serve ${CLAUDE_PROJECT_DIR}
$ npx degit NickCirv/engram/plugins/anthropic-marketplace/engram/skills/cost .claude/skills/cost
$ npx degit NickCirv/engram/plugins/anthropic-marketplace/engram/skills/mistakes .claude/skills/mistakes
$ npx degit NickCirv/engram/plugins/anthropic-marketplace/engram/skills/query .claude/skills/query

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
engram-serve · "engram" binary 2.5k

Skills (3)

costmistakesquery

Similar rigs

Republicofhaitigoodstory6175/engram
Connect your codebase to AI coding tools with a universal context spine.
★ 1 project Claude CodeCodexCursor 1 mcp 3 skills today
Pragmatist 3.5k tok ·
MetamusicX/zissa-wiki
Zissa Wiki — an LLM-maintained research knowledge base in plain markdown, maintained by any AI agent (Claude, Codex, Gemini, DeepSeek, Kimi, Grok, Mistral or any chat app). Implements Karpathy's LLM Wiki pattern; checks every quote against
★ 58 project Claude CodeCodexGemini CLI 3 skills 1 hooks 13d ago
Pragmatist 4.4k tok ·
ArtemXTech/claude-code-obsidian-starter
Free starter kit: Claude Code + Obsidian. Pre-configured vault with skills for projects, tasks, clients, and daily routines. Just open and go.
★ 224 project Claude Code 5 skills 4d ago
Pragmatist 466 tok ·
chicken-noodle-chris/tome
Tome is a Claude Code plugin and a CLI tool with skills and scripts to create an llm-wiki based on karpathy's suggestion, with a quartz rendering layer for enhanced user readability, and a CLI that keeps the content to-spec. It's meant to
★ 7 project Claude Code 6 skills 2mo ago
Pragmatist 650 tok ·
copied ✓