vectorize-io/hindsight is an agent memory system that stores experiences and helps AI agents learn over time instead of only recalling conversation history. It is used by developers adding long-term memory to agents, including coding agents. Catalogue add-ons connect agents to Hindsight and its memory workflows.
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 skills add vectorize-io/hindsight --skill memory-setupgit clone --depth 1 https://github.com/vectorize-io/hindsightWrote 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/skills/vectorize-io/hindsight/memory-setup)<a href="https://agentmods.dev/skills/vectorize-io/hindsight/memory-setup"><img src="https://agentmods.dev/badge/skills/vectorize-io/hindsight/memory-setup/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.
<a href="https://agentmods.dev/skills/vectorize-io/hindsight/memory-setup"><img src="https://agentmods.dev/badge/skills/vectorize-io/hindsight/memory-setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00046 | $0.00617 |
| Opus 5.5 | $0.00018 | $0.00247 |
| Sonnet 5.5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
memory-setup 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 13d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up Hindsight memory
Hindsight stores memory in banks. This plugin uses three kinds:
- This Bot's bank,
grok-bot::<bot-name>: what this Bot learns in its own work. Build<bot-name>from the Bot's name, lowercase, with spaces turned into hyphens (a Bot named "Sales Researcher" usesgrok-bot::sales-researcher). When you are not a Grok Bot (for example, an agent in Cursor), this bank is per project instead:cursor::<project-name>, from the open workspace folder's name in the same lowercase, hyphenated form. With no workspace open, ask the user what to call it. Never use another Bot'sgrok-bot::bank as your own; those are read-only to you. - The shared bank,
grok-bot::shared: what every Bot on this account should know. - The user's other banks: memory written by the user's other AI tools, such as Claude Code or ChatGPT. Read these when a task touches that work. Never write to them.
Steps
- Call
list_banks. A successful call proves the connection is real. If it fails, tell the user to reconnect Hindsight in the plugin's settings and stop. Do not guess endpoints or hostnames. - If you are a Grok Bot that still has the default name "Grok Bot", ask the user what to call it before going further. The name becomes the bank id, so a default name would give every unnamed Bot the same bank, and renaming later strands its memory under the old id.
- If this Bot's bank does not exist, call
create_bankwith itsbank_idand anameof "Grok Bot: ". - If
grok-bot::shareddoes not exist, callcreate_bankwithname"Grok Bot: shared". - Call
list_mental_modelsongrok-bot::shared. If there is no mental model named "About the user", callcreate_mental_modelon that bank with that name and the source query "Who is this user: their work, current projects, the people they mention most, and their stated preferences". - Tell the user which banks exist and which other banks you can read.
Rules
- Never call
delete_bank,clear_memories,invalidate_memory,delete_documentordelete_mental_model. If something should be deleted, tell the user and let them do it. - Never store passwords, one-time codes, API keys, card or account numbers.
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.
- 13d ago First seen · 28 lines · 46 tokens per session scan A 0a8c6bf59ea1
memory-setup is a skill published in the GitHub repository vectorize-io/hindsight (50,054 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 617 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".
session-summaries
What the chat right-panel session summary shows, what it costs, and how to make a session summarize well. Load when the user asks about the session summary panel, why a summary looks wrong or empty, or how to turn it on.
semantix
Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.
search-shared-sessions
Search an Agent Relay workspace's shared coding-agent sessions for prior work, decisions, fixes, or the context behind a task or pull request. Use when team history could answer the user's question or prevent repeating an investigation.
memory-audit-belief-duel
A guided review process for conflicting beliefs or memories. It examines cases where two conclusions cannot both be true, including conflicts between a general rule and a more specific memory.
memory-audit-discoverability
A review guide for checking whether stored memories can be found at the right time. It focuses on where memories are attached, when they are triggered, whether aliases are missing, and whether a parent has too many children.