cognicore-dev/cognicore-env
Persistent memory, reflection & safety for AI agents. No vector DB, no embedding server — BM25 + multi-hop retrieval runs in-process. MCP server with 10 tools. Apache 2.0.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http cognicore-env https://mcp.cognicoree.tech/mcp/stream $ claude mcp add --transport http cognicore https://mcp.cognicoree.tech/mcp/stream $ npx degit cognicore-dev/cognicore-env/skills ./rig-cognicore-env/skills
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 --transport http cognicore-env https://mcp.cognicoree.tech/mcp/stream $ claude mcp add --transport http cognicore https://mcp.cognicoree.tech/mcp/stream
$ npx degit cognicore-dev/cognicore-env/plugins/cognicore-experience/skills/structured-experience .claude/skills/structured-experience $ npx degit cognicore-dev/cognicore-env/plugins/cognicore-memory/skills/memory .claude/skills/memory $ npx degit cognicore-dev/cognicore-env/skills/never-twice .claude/skills/never-twice
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 (3)
| server | source | est. tokens |
|---|---|---|
| mcp.cognicoree.tech · "cognicore-env" | remote · remote | 2.5k |
| cognicore-experience | local / custom | 2.5k |
| mcp.cognicoree.tech · "cognicore" | remote · remote | 2.5k |
Skills (3)
Similar rigs
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
trags-garden/poppy
Poppy: local-first memory CLI for AI coding agents. Remember what matters.
Pragmatist 2.6k tok · · Q0
WizardingCode-io/wizardingcode-mem
Memory for coding agents. What one session learns, the next one is told — Claude Code, Codex, Gemini CLI, OpenCode, Cursor. One local binary, no daemon, no model in the loop. A WizardingCode product.
Pragmatist 11.4k tok · · Q10
atlaso-labs/cursor
Persistent memory for Cursor: automatic capture as you work, recall through a generated rules file, the same memory in Claude Code and Codex. Hooks, the Atlaso MCP server, a skill and rules. By Atlaso.
Pragmatist 2.8k tok · · Q0