Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/kurcontko/mnemotree/agents-mdgit clone --depth 1 https://github.com/kurcontko/mnemotreeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/kurcontko/mnemotree/agents-md)<a href="https://agentmods.dev/instructions/kurcontko/mnemotree/agents-md"><img src="https://agentmods.dev/badge/instructions/kurcontko/mnemotree/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00368 | $0.00368 |
| Opus 5 | $0.00184 | $0.00184 |
| Sonnet 5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
mnemotree AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Mnemotree
Project Summary
Mnemotree is a Python 3.10+ library for giving LLM agents biologically-inspired, persistent memory. The core API (MemoryCore) supports storing memories, recalling them via semantic similarity + filters, and optional analysis/enrichment (importance scoring, emotions, entities/keywords). It also ships a ready-to-run MCP server (mnemotree-mcp) so tools like Codex CLI / Claude Desktop can use the memory store over stdio or HTTP.
Key locations:
- Core API:
src/mnemotree/core/(MemoryCore, models, retrieval/scoring) - Storage backends:
src/mnemotree/store/(ChromaDB, SQLite+sqlite-vec, Neo4j, Milvus) - MCP server:
src/mnemotree/mcp/server.py - CLI entry points:
src/mnemotree/cli.py - Examples:
examples/(Streamlit chat app inexamples/memory_chat/) - API stability policy:
docs/API.md(public vs experimental internals)
Common Commands
Install (pip)
python -m venv .venv
source .venv/bin/activate
pip install -e .
# Optional extras, e.g.:
# pip install -e ".[dev]"
# pip install -e ".[lite,chroma]"
Install (uv)
uv venv
uv pip install -e .
# Optional extras, e.g.:
# uv pip install -e ".[dev]"
# uv pip install -e ".[lite,chroma]"
Common Make targets
make lint
make typecheck
make test
make build
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 43 lines · 368 tokens per session scan A f853584ac7e7
mnemotree AGENTS.md is an instructions file published in the GitHub repository kurcontko/mnemotree (6 stars, last pushed 3mo ago), licensed MIT. It adds 368 tokens to every session, about $0.0018 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
annal CLAUDE.md
Claude Code instructions for heyhayes/annal, covering annal — semantic memory mcp server, what this is, project structure, commands and install (editable with dev deps).
mempalace CLAUDE.md
Claude Code instructions for MemPalace/mempalace, covering claude.md, the mission, design principles, contributing and setup.
llm-wiki-memory AGENTS.md
Instructions for ctxr-dev/llm-wiki-memory, covering agents.md, development discipline (.agents/), layout, tests and conventions.
engram-mcp CLAUDE.md
Claude Code instructions for edg-l/engram-mcp, covering engram mcp, development rules, structure, key types and mcp capabilities.
palaia AGENTS.md
AGENTS.md instructions for byte5ai/palaia, covering agent instructions, git workflow, pull requests, project and pre-push hook.
OpenNotebookLM AGENTS.md
AGENTS.md instructions for tom1030507/OpenNotebookLM, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.