An integration guide for adding persistent, structured memory to an AI agent. It describes storing facts, past interactions, entities, and preferences, then retrieving relevant context later.

Use it when building, debugging, or evaluating an agent that needs long-term memory across sessions.

It helps an agent retain useful information across conversations instead of relying only on the current context window.

synap — Skill for Claude Code and Codex by maximem-ai

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.

Any agent

npx skills add maximem-ai/maximem_synap_sdk --skill synap-codex

Clone the repo

git clone --depth 1 https://github.com/maximem-ai/maximem_synap_sdk

Made for: Claude Code, Codex.

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/skills/maximem-ai/maximem_synap_sdk/synap-codex/github.svg)](https://agentmods.dev/skills/maximem-ai/maximem_synap_sdk/synap-codex)

Your own site

<a href="https://agentmods.dev/skills/maximem-ai/maximem_synap_sdk/synap-codex"><img src="https://agentmods.dev/badge/skills/maximem-ai/maximem_synap_sdk/synap-codex/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/maximem-ai/maximem_synap_sdk/synap-codex"><img src="https://agentmods.dev/badge/skills/maximem-ai/maximem_synap_sdk/synap-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,694 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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 5.1	$0.00000	$0.01694
Opus 5	$0.00000	$0.00847
Sonnet 5	$0.00000	$0.00339
Haiku 4.5	$0.00000	$0.00169

Measured 9d ago against content hash 57b569290248, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

synap scanned grade A with 1 finding 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 9d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (examples/python-minimal.py, examples/typescript-minimal.ts, scripts/verify_synap.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Four fetch interfaces: match retrieval to the scope you ingested at:** `sdk.user.context.fetch(user_id=...)`, `sdk.customer.context.fetch(customer_id=...)` (B2B only, rejected on B2C), `sdk.client.context.fetch()`, `

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

synap-codex — 91% identical, 12 lines differ

skills/synap-codex/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maximem Synap — Agent Memory Skill (Codex)

Synap is a managed memory layer for AI agents: it ingests conversations/documents, extracts structured knowledge (facts, preferences, episodes, entities), and serves ranked, scope-aware context back at retrieval time. No vector DB to run, no retrieval pipeline to build.

This is the Codex edition. The integration knowledge — reference/, scripts/, examples/ — is byte-for-byte identical to the Claude Code skill; only this manifest and AGENTS.md differ. Read only the reference files you actually need.

Sandbox & approvals (read first)

This skill does real work in the user's repo, so the procedure needs capabilities Codex gates behind approval. State what you need before you start; don't assume silent execution:

Network access — to pip install maximem-synap / npm install @maximem/synap-js-sdk and the framework package, and for the SDK to reach Synap Cloud at runtime.
File writes — to add integration code and (if missing) a git-ignored .env.
A secret — the synap_... API key. Ask the user to provide it; never print it back or commit it.

If running with restricted network/filesystem, tell the user which commands to run themselves.

Procedure — the order to do this in

There is no CLI. Provisioning happens by hand in the dashboard; the SDK only uses a key that already exists. Do not skip the PAUSE.

Detect the stack. Identify the user's framework (or "custom"). This selects which reference/frameworks/<name>.md to follow — see reference/frameworks/_index.md.
Provision in the dashboard (manual). Walk the user through reference/dashboard-setup.md: sign up → create Client → create Instance (+ upload a use-case .md, see reference/use-case-markdown.md) → set B2C/B2B → generate an API key.
⏸ PAUSE. Ask the user to paste their synap_... key (or set it themselves), then export SYNAP_API_KEY=synap_... and export SYNAP_INSTANCE_ID=inst_... (the dashboard shows both together). Do not write integration code before the key is set.
Install. The SDK + the framework package (needs network + approval — see "Sandbox & approvals"). Details in reference/sdk-setup.md.
Integrate. Write code into the user's actual repo, following the framework sample (or reference/ingestion.md + reference/context-fetch.md for a custom stack).
Verify. Run python scripts/verify_synap.py. Never report done without a green run.

Read the full file on GitHub · 64 lines

Files

What ships with it

34 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

9d ago First seen · 64 lines · 0 tokens per session scan A 57b569290248

Subscribe to this mod's changes

synap is a skill published in the GitHub repository maximem-ai/maximem_synap_sdk (64 stars, last pushed 8d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,694 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and context agent-memory ai ai-agents ai-memory autogen context

deja-search

Search deja before re-deriving past work: when the user refers to earlier sessions or decisions, before debugging an error, and before implementing something that may already exist. It searches this machine's own history across every AI coding tool used on it, going back further than deja itself was installed.

vshulcz/deja-vu · 57 tokens

deja-history

Search the user's past AI coding sessions. Use when they say things like 'didn't we fix this before', 'what did we decide about X', or before re-debugging an error that may already be solved.

vshulcz/deja-vu · 47 tokens

plur-memory

Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.

plur-ai/plur · 31 tokens

dashboard

Open OwnMem Console, the local dashboard for this repository's memory. Use when the user asks to open the dashboard, see memory metrics, check adoption or recall quality, or set up the optional embedding lane. Requires a repository initialized with the dashboard layer.

grpcer/ownmem · 53 tokens

Effective Memory

The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.

plur-ai/plur · 44 tokens

plur-session-end

Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.

plur-ai/plur · 35 tokens

synap