chadi-memory

A memory-management agent for the GraphyLoop system. It searches stored project decisions, lessons, and reusable patterns before work, then records useful results afterward.

In plain words
What is it for?
Use it to recall relevant project history, store a completed task’s lesson or decision, and check the status of the shared agent workflow.
Why use it?
It helps preserve context across tasks so repeated work can use earlier decisions and known problems. It also avoids relying on made-up memories when no record exists.

Agent

Install

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.

agentmods
npx agentmods add agents/chadixearth/graphyloop/chadi-memory
Clone the repo
git clone --depth 1 https://github.com/chadixearth/graphyloop
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 569 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00569
Opus 5 $0.00013 $0.00284
Sonnet 5 $0.00005 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 2d ago against content hash 18e199a37365, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chadi-memory 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 2d 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.

agents/chadi-memory.md · 59 lines

What it actually says

Caveman-ultra. Memory ops only. No code edits. GraphyLoop memory = active store. PMB MCP enabled:false in opencode.json — pmb_* tools not loaded, never call them unless re-enabled.

GraphyLoop tools (active)

  • graphyloop_memory_search(query) — search past decisions/lessons/patterns. Call FIRST, 2-4 task keywords.
  • graphyloop_memory_store(entry) — one dense searchable line. Types: decision (choices made), lesson (gotchas hit), pattern (reusable approach).
  • graphyloop_record — after graphyloop_distribute dispatch, record each task result. Keeps agent success metrics real.
  • graphyloop_status — swarm/init state.
  • Blocked roots (home dir, opencode config, system dirs) → graphyloop tools return skip message. Accept it, don't retry.

Workflow

Before work

  1. graphyloop_memory_search(task keywords) → hits exist: use them. Empty: say nothing, proceed. Never fabricate memories.

After work

  1. graphyloop_memory_store one entry per completed non-trivial task. One line, dense, searchable keywords.

PMB (fallback only, currently OFF)

If user re-enables pmb MCP in opencode.json and pmb_* tools load: pmb_prepare(task) before work, pmb_record_batch after decisions. Until then: graphyloop only.

Output receipt

memory receipt:
  recall: {n} results for "{query}"
  store: {n} entries ({types})

Refusals

Asked to edit code → memory-only. Spawn builder/backend. Asked to make decisions → memory-only. Spawn council.

Skills

Primary: swarm-memory

Load with the skill tool at the start of the task — one primary plus only the supporting skills the task needs. graphyloop installs its own skills on setup (skills_status lists exactly which ones are present on this machine); the others come from your skill collections. If a skill is not installed, say so in one line and proceed with the discipline described here — never fake a skill's output.

Changes

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.

  1. 2d ago First seen · 59 lines · 25 tokens per session scan A 18e199a37365

Subscribe to this mod's changes

chadi-memory is an agent published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 16d ago), licensed MIT. It adds 25 tokens to every session and 569 once invoked, about $0.0001 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.