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/chandra447/pi-hermes-memory/agents-mdgit clone --depth 1 https://github.com/chandra447/pi-hermes-memoryWrote 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/chandra447/pi-hermes-memory/agents-md)<a href="https://agentmods.dev/instructions/chandra447/pi-hermes-memory/agents-md"><img src="https://agentmods.dev/badge/instructions/chandra447/pi-hermes-memory/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 | $0.00870 | $0.00870 |
| Opus 5 | $0.00435 | $0.00435 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
pi-hermes-memory 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pi Hermes Memory Extension
Project Overview
This is a Pi coding agent extension that brings Hermes-style persistent memory and a learning loop to any Pi user. After pi install, users get persistent memory across sessions, a background learning loop, and session-end flush.
v0.1 is complete (119 tests, v0.1.0 tagged). Current work is v0.2: Skills + Smart Curation — see docs/0.2/TASKS.md.
Architecture
- Language: TypeScript (loaded via jiti, no compilation needed at runtime)
- Runtime: Pi extension API (
@earendil-works/pi-coding-agent) - Storage: Two markdown files (
MEMORY.md,USER.md) in~/.pi/agent/memory/ - Entry point:
src/index.ts— registers tools, event handlers, and commands
Key Files
| File | Purpose |
|---|---|
src/index.ts |
Extension entry point — wires all components together |
src/types.ts |
Shared TypeScript interfaces + getMessageText() helper |
src/constants.ts |
Prompts, defaults, delimiter |
src/store/memory-store.ts |
Core MemoryStore class — CRUD, persistence, frozen snapshot |
src/store/content-scanner.ts |
scanContent() — injection/exfiltration detection |
src/tools/memory-tool.ts |
registerMemoryTool() — LLM tool definition |
src/handlers/background-review.ts |
setupBackgroundReview() — learning loop via pi.exec |
src/handlers/session-flush.ts |
setupSessionFlush() — pre-compaction/shutdown flush |
src/handlers/insights.ts |
registerInsightsCommand() — /memory-insights command |
PLAN.md |
Full v0.1 implementation plan with Hermes source file reference map |
docs/ROADMAP.md |
Full roadmap with Hermes competitive analysis + gap analysis |
docs/0.2/TASKS.md |
v0.2 task breakdown — Skills + Smart Curation |
Design Decisions
- Frozen snapshot — Memory is injected into system prompt once at session start, never mutated mid-session (preserves Pi's prompt caching)
- Atomic writes — Temp file +
fs.rename()for crash safety pi.exec()for background review — Stays within Pi's intended extension API§delimiter — Same as Hermes for consistency- No SQLite — Pi has its own
SessionManager, we read from it directly
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 · 78 lines · 870 tokens per session scan A 40bb562bec5f
pi-hermes-memory AGENTS.md is an instructions file published in the GitHub repository chandra447/pi-hermes-memory (408 stars, last pushed 4d ago), licensed MIT. It adds 870 tokens to every session, about $0.0043 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 2026-08-30.
Other instructions, from other repositories
cognirepo CLAUDE.md
Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).
openexp CLAUDE.md
Instructions for anthroos/openexp, covering openexp — development instructions, memory protocol (mandatory), before starting any task, after completing a task and when the user shares context.