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 hindsight-localgit 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/hindsight-local)<a href="https://agentmods.dev/skills/vectorize-io/hindsight/hindsight-local"><img src="https://agentmods.dev/badge/skills/vectorize-io/hindsight/hindsight-local/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/hindsight-local"><img src="https://agentmods.dev/badge/skills/vectorize-io/hindsight/hindsight-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 15 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 21 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 44 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 45 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 46 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 63 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 64 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 72 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00032 | $0.01006 |
| Opus 5.5 | $0.00013 | $0.00402 |
| Sonnet 5.5 | $0.00006 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
hindsight-local 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- hindsight-local — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hindsight Memory Skill (Local)
You have persistent memory via the hindsight-embed CLI. Proactively store learnings and recall context to provide better assistance.
Setup Check (First-Time Only)
Before using memory commands, verify Hindsight is configured:
uvx hindsight-embed daemon status
If this fails or shows "not configured", run the interactive setup:
uvx hindsight-embed configure
This will prompt for an LLM provider and API key. After setup, the commands below will work.
How Hindsight Works
When you call retain, Hindsight does not store the string as-is. The server runs an internal pipeline that:
- Extracts structured facts from the content using an LLM
- Identifies entities (people, tools, concepts) and links related facts
- Builds temporal and causal relationships between facts
- Generates embeddings for semantic search
This means you should pass rich, full-context content — the server is better at extracting what matters than a pre-summarized string. Your job is to decide when to store, not what to extract.
Commands
Store a memory
Use memory retain to store what you learn. Pass the full context — raw observations, session notes, conversation excerpts, or detailed descriptions:
uvx hindsight-embed memory retain default "User is working on a TypeScript project. They enabled strict mode and prefer explicit type annotations over inference."
uvx hindsight-embed memory retain default "Ran the test suite with NODE_ENV=test. Tests pass. Without NODE_ENV=test, the suite fails with a missing config error." --context procedures
uvx hindsight-embed memory retain default "Build failed on Node 18 with error 'ERR_UNSUPPORTED_ESM_URL_SCHEME'. Switched to Node 20 and build succeeded." --context learnings
You can also pass a raw conversation transcript with timestamps:
uvx hindsight-embed memory retain default "[2026-03-16T10:12:03] User: The auth tests keep failing on CI but pass locally. Any idea?
[2026-03-16T10:12:45] Assistant: Let me check the CI logs. Looks like the tests are running without the TEST_DATABASE_URL env var set — they fall back to the production DB URL and hit a connection timeout.
[2026-03-16T10:13:20] User: Ah right, I never added that to the CI secrets. Adding it now.
[2026-03-16T10:15:02] User: That fixed it. All green now." --context learnings
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.
- 1mo ago First seen · 112 lines · 32 tokens per session scan A a7cda72a99fe
hindsight-local is a skill published in the GitHub repository vectorize-io/hindsight (51,231 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,006 once invoked, about $0.0001 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 2026-08-30.
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.