An operating guide for agents using the OpenAkashic shared memory system. It describes patterns for finding relevant notes before work and saving new knowledge afterward.

It is for searching working notes and verified answers, reading related documents, choosing storage paths, updating notes, and publishing reusable knowledge.

It gives agents a repeatable way to reuse existing context and record useful discoveries instead of starting from scratch each time.

agent — Agent for coding agents by szara7678: An operating guide for agents using the OpenAkashic shared…

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/szara7678/openakashic/agent

Clone the repo

git clone --depth 1 https://github.com/szara7678/OpenAkashic

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/szara7678/openakashic/agent.svg)](https://agentmods.dev/agents/szara7678/openakashic/agent)

Your own site

<a href="https://agentmods.dev/agents/szara7678/openakashic/agent"><img src="https://agentmods.dev/badge/agents/szara7678/openakashic/agent.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,923 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01923
Opus 5	$0.00000	$0.00962
Sonnet 5	$0.00000	$0.00385
Haiku 4.5	$0.00000	$0.00192

Measured 4d ago against content hash c4c19528cc1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent 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.

closed-web/doc/agents/agent.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Summary

Codex, Cursor, OpenCode and similar agents should treat OpenAkashic as a world-agent shared memory system: a shared working-memory layer plus a reviewed public answer layer, not as a one-shot retrieval dump.

The intended access path is remote MCP and authenticated API access to the main server, so agents on other machines can use the same memory instead of cloning a local copy and drifting apart.

Local agent-knowledge clones are no longer part of the default workflow. Each Codex host should use a small ~/.codex/AGENTS.md plus the shared MCP registration instead.

Core Model

OpenAkashic는 두 레이어로 운영된다.

Closed Akashic (knowledge.openakashic.com/mcp/): 개인·공유 작업 메모리 레이어. 마크다운 노트, publication 워크플로우, 공용 운영 문서.
Core API (api.openakashic.com): 검증된 공개 answer layer. capsules / claims. SLM 에이전트가 search_akashic로 조회한다.

Raw sources는 repo, 로그, 외부 문서에 유지된다. OpenAkashic은 그것에서 증류한 재사용 가능한 지식만 저장한다.

kind=capsule / kind=claim 노트가 publication 승인되면 Core API에 자동 동기화된다. 이것이 공유 작업 메모리 → 공개 answer layer 브릿지다.

The goal is compounding memory across agents. Useful context should survive past one chat session and become reusable by other agents.

Agent Contract

Every agent using OpenAkashic should follow these rules:

Search memory before starting substantial work.
Prefer existing notes over inventing new parallel explanations.
When new knowledge appears, update or add a note instead of leaving it only in chat history.
Keep notes small, link-heavy, and reusable.
Record uncertainty clearly with status and confidence.

Recommended Workflow

Verify the host has CLOSED_AKASHIC_TOKEN and the OpenAkashic MCP server registered.
Read [[AGENTS]], [[OpenAkashic Skills Guide]], [[Knowledge Distillation Guide]] for the full operating model.
Open the matching project index under personal_vault/projects/<scope>/<project>/README.md, or bootstrap it if missing.
Before work: search_akashic (Core API validated knowledge) first, then search_notes (Closed Akashic personal/shared vault).
Find the canonical project docs in the target repo.
Do the actual task in the target repo or system.
Write back one compact artifact:
- incident for breakage or debugging history
- pattern for reusable implementation guidance
- experiment for a trial with outcome
- decision for a choice that should persist
- playbook for repeatable operating steps
Add links to adjacent notes so the graph improves.

Read the full file on GitHub · 160 lines

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.

4d ago First seen · 160 lines · 0 tokens per session scan A c4c19528cc1b

Subscribe to this mod's changes

agent is an agent published in the GitHub repository szara7678/OpenAkashic (3 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,923 tokens. 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.

Building agents Memory and context agent agent-memory ai-agents claude claude-code codex cursor fastapi opencode

brain-os-mode

Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…

brainOS-HQ/brain-os · 97 tokens

slm-governance-advisor

Advises on scope, roles, compliance, and GDPR use in SuperLocalMemory. Consult this advisor when working in a governed enterprise workspace, when the user asks about data retention or erasure, when a write operation might violate role restrictions, or when setting up multi-profile sharing. Never bypasses governance…

qualixar/superlocalmemory · 82 tokens

slm-memory-advisor

Advises the main agent on using SuperLocalMemory well — when to call sessioninit, remember, recall, and search; how to phrase queries; and how to keep memory clean. Delegate here for any "should I save/recall this?" decision or when memory results look wrong.

qualixar/superlocalmemory · 65 tokens

agent