hindsight
Give GitHub Copilot CLI a Memory of Your Codebase
GitHub Copilot CLI forgets your project between sessions. Add Hindsight so it recalls past decisions and retains what it learns, automatically via hooks.
How to Move Your Agent's Memory Off a Vector Database
A practical guide to migrating agent memory off a vector database like Pinecone or Chroma to Hindsight: what to export, how to map it, and what you gain.
8 Agent Memory Use Cases (With Real Examples)
The real agent memory use cases teams build on Hindsight, from coding agents to customer-facing products to automations, each with a concrete example.
recall vs reflect: Search Your Agent's Memory, or Ask It
Hindsight gives your agent two ways to read its memory. recall retrieves the relevant facts (no LLM, instant). reflect reasons across them to synthesize an answer. When to use each.
Give Roo Code a Memory So Every Task Builds on the Last
Roo Code runs autonomous coding tasks but starts each one from zero. Add Hindsight agent memory: recall context before every task, retain a summary after.
Your 1M-Token Context Window Is Not Memory
A context window is working memory: it forgets everything when the session ends and degrades long before it fills. Why a bigger window is still not agent memory.
Mira Murati's Thinking Machines Dropped Inkling. We Made It Your Agent's Memory in 5 Minutes.
Thinking Machines open-sourced Inkling. We made it an AI agent's long-term memory in four env vars, and it resolved 'last week' to a real date on the first try. Here is how.
Give ZCode a Long-Term Memory That Follows You Between Tools
ZCode is Z.ai's GLM desktop coding agent. Add Hindsight for persistent memory via plain Python hooks, no MCP, shared with Claude Code and Cursor.
The Fully Open Agent Memory Stack: Self-Hosting Hermes + Hindsight
Most agent-plus-memory stacks have a closed core: a frontier API model, a proprietary memory service, or both. Hermes and Hindsight are the exception. Every layer is open source and can run on your own hardware with no external calls.
One Bank or Many? A Field Guide to Structuring Agent Memory
Every Hindsight integration tells you to set a bank_id, but not how to decide what a bank should be. A bank is a recall boundary: how to scope agent memory, and when to reach for tags instead.
Give Every Agent You Run in Omnigent a Persistent Memory
Omnigent wraps any AI agent: Claude Code, Codex, Cursor, Hermes, and more. Add Hindsight once and every harness it orchestrates gets recall, retain, and reflect from a single setup.
Inside retain(): What Actually Happens When Your Agent Remembers
Calling retain() is one line of code. Underneath, a sentence becomes extracted facts, resolved entities, a knowledge graph, and consolidated observations. Here is the whole write path.
One Memory, Three Surfaces: A Day With Cursor, OpenClaw, and Vapi
We pointed our code editor, our Slack agent, and our voice agent at one shared Hindsight memory. Here is a day in that workflow, and what actually changed.
Give Aider a Memory That Outlives the Session
Aider is a sharp terminal pair programmer that forgets everything when it exits. hindsight-aider wraps the command so it recalls your project's decisions before each session and retains what it learns after.
Give Zed's AI Assistant a Persistent Memory
The Zed editor's AI assistant is sharp inside a task and a stranger between them. hindsight-zed gives it long-term memory that recalls and retains across sessions.
Teach Vercel Eve to Remember: Automatic Agent Memory
Vercel Eve agents get automatic long-term memory with hindsight-eve v0.2.0: context injected before every turn, each exchange saved after, no model tool call.
From Documents to Decisions: architxt and Hindsight
How architxt uses Hindsight as a time-aware agent memory layer to turn fragmented enterprise architecture documents into a queryable, current-state Temporal Mosaic.
Devin Desktop Persistent Memory (Formerly Windsurf)
Add persistent memory to Devin Desktop (formerly Windsurf): a remote MCP server plus one always-on rule that recalls at task start and retains as you work.
Entity Resolution in Agent Memory: One Person, Many Names
How agent memory decides that Sarah, Sarah Chen, and she are one person, and why Hindsight resolves entities with a co-occurrence graph, not embeddings.
Zapier Persistent Memory: Actions and Triggers
The Hindsight app for Zapier adds persistent memory to any Zap: Retain, Recall, and Reflect actions, plus triggers that start Zaps from memory events.
Structuring Chat Logs for Agent Memory
The shape of your chat logs decides your agent's memory quality. Retain whole conversations, label who is speaking, set context, and anchor in time.
Persistent Memory for the Vercel AI SDK in Five Tools
Add long-term memory to any Vercel AI SDK app with Hindsight. Five ready-to-use tools for retain, recall, and reflect that work with generateText, streamText, and ToolLoopAgent, on any model provider.
Hindsight Is Now a One-Click Memory Provider in the Hermes Desktop App
Hermes Agent's desktop app now lets you pick Hindsight as your memory provider and configure it entirely in-app — pick a mode, paste an API key, done. No config files, no .env editing. And it's the only memory backend that gets a full settings panel.
OpenHands (formerly OpenDevin) Forgets Every Task. Here's the One-Command Fix.
Add persistent long-term memory to OpenHands (formerly OpenDevin) with Hindsight. One command wires the Hindsight MCP server into config.toml and drops a recall/retain rule into AGENTS.md, so the agent recalls relevant context at the start of every task and retains durable facts as it works.
Stop Building Microsoft Agent Framework Agents That Forget
Add persistent long-term memory to Microsoft Agent Framework agents with Hindsight. Plug in one context provider and every run recalls relevant memories and retains the conversation automatically. No MCP, no tools the model has to remember to call.
Staleness-Aware Memory: When Your Agent Should Verify Before It Trusts
Hindsight's consolidated memory (observations and mental models) is derived from raw facts, so it can lag behind new writes. Instead of silently serving a stale snapshot, Hindsight flags how far behind each layer is, and the reflect agent verifies against raw facts before trusting it.
Chat With Your Obsidian Vault: Grounded Answers That Cite Your Notes
Give your Obsidian vault an AI agent that actually knows your notes. The Hindsight plugin syncs your vault into a memory bank and adds a chat panel whose answers are grounded on your notes and cite the source, with your vault staying the single source of truth.
Gemini Spark Persistent Memory: Agent-Initiated Recall Over MCP
Add persistent long-term memory to Google's Gemini Spark assistant with Hindsight. No plugin host, no hooks. Spark calls Hindsight's recall and retain tools over MCP, with Hindsight Cloud or a self-hosted OAuth proxy.
Cursor Persistent Memory: One Bank for the Editor and the CLI
Two new Hindsight integrations give Cursor persistent long-term memory: one for the Cursor editor (with a workaround for the broken sessionStart additionalContext channel in Cursor 3.x) and one for Cursor CLI. Both can share the same memory bank.
Haystack Persistent Memory: Drop-In Tools and Auto-Recall for Any Agent
Add persistent long-term memory to any Haystack agent with Hindsight. Three Haystack Tools (retain, recall, reflect) plus an optional HindsightMemoryWrapper that injects memories before each turn and stores the transcript after.
Flowise Persistent Memory: Drop-In Tool Nodes for Any Chatflow
Add persistent long-term memory to any Flowise chatflow or agent with Hindsight. Three Tool nodes (Retain, Recall, Reflect) drop straight into a Conversational Agent and share one Hindsight API credential.
Cline Persistent Memory: Lifecycle Hooks Instead of MCP
Add persistent memory to Cline with Hindsight using lifecycle hooks. No MCP server, no model tool-calling required. Hooks deterministically recall context before each task and retain what happened after.
How oh-my-pi Built Persistent Codebase Memory on Hindsight
oh-my-pi — a 10k-star terminal coding agent — uses Hindsight as its long-term memory backend. Here's a walkthrough of the integration: bank scoping, mental-model seeding, and the auto-retain pipeline, with code straight from the repo.
How Hindsight Learns: A Deep Dive Into Mental Models
Mental models are the top tier of Hindsight's learning hierarchy — persistent, self-refreshing understandings of the topics your agent asks about every session. A walkthrough from the schema up.
Long-Term Memory for Google ADK Agents with Hindsight
Add persistent long-term memory to Google ADK agents with Hindsight. Drop-in BaseMemoryService for automatic retain on session end and recall on search_memory — plus explicit retain/recall/reflect tools when you want them.
Voice Agents That Remember: Adding Memory to Vapi with Hindsight
Add persistent long-term memory to Vapi voice AI calls with one webhook. Recall caller history at call start, retain the transcript at call end — no per-turn integration needed.
Using Entity Labels to Automatically Tag Memories in Hindsight
Hindsight's entity labels turn free-text memories into structured, filterable classifications — automatically. A controlled vocabulary, four label types, and one tag: true switch that turns labels into filterable tags.
Hermes Agent on Windows: Set Up Persistent Memory with Hindsight
Nous Research just shipped Hermes Agent native on Windows. Here's how to give it persistent memory with Hindsight — one command, three modes, no Docker or WSL.
Building a Hermes Coding Assistant on Windows That Remembers Your Codebase
Nous Research just announced Hermes Agent native on Windows. Here's how to add persistent codebase memory with Hindsight — no Docker, no WSL, PowerShell start to finish.
Building an OpenClaw Coding Agent That Remembers Your Codebase
OpenClaw with Hindsight remembers your codebase across sessions — conventions, past bugs, architectural decisions. Setup in 2 minutes.
Building a Hermes Coding Assistant That Remembers Your Codebase
Hermes Agent with Hindsight remembers your codebase across sessions, conventions, past bugs, architectural decisions. Setup in 2 minutes.
The Consolidation Problem in Agent Memory
Agents that remember everything remember nothing useful. A four-lever framework — importance, merge, decay, eviction — for consolidating agent memory.
Onboarding a New Engineer Onto Five Months of OpenCode Memory
A new engineer joins a codebase the team has been working in for five months. With OpenCode + Hindsight, day one looks very different from the README.
The Case Against External Vector DBs for Agent Memory
Most 'add memory to your agent' tutorials start with installing a vector database. They shouldn't. Why vector DBs are the wrong default for agent memory.
The Memory Layer Every n8n Workflow Was Missing
Hindsight's new community node adds persistent memory to any n8n workflow — Retain, Recall, Reflect. Workflows compound across runs instead of resetting.
Your Claude Code Subagents Don't Share What They Learn
Claude Code subagents (Plan, Explore, general-purpose, custom) each spawn fresh and discard everything they discover. Here's how to give them shared memory.
The Missing Layer in Every Agent Harness
Modern agent harnesses ship with tools, MCP, and IDE integrations — but no memory. Why that's the missing layer, and how harnesses are starting to fix it.
Your Agent Is Not Forgetful. It Was Never Given a Memory.
Why agents seem forgetful, and why memory is different from context windows and retrieval. How Hindsight adds long-term memory to agents.
Your AI's Memory Is a Black Box. Constellation View Makes It Visible.
Constellation View and the Entity Co-occurrence Graph let you inspect the structure of a Hindsight bank as an interactive graph — debug memory quality, spot noisy hubs, and explain agent recall visually.
How I Built Multi-User AI Memory into a Financial Product from Day One
A fintech co-founder shares how he integrated Hindsight into a financial AI system from the start, using self-hosted deployment and tag-based isolation for multi-user memory.
Your Agent Memory Setup Keeps Drifting. Hindsight 0.5.0 Adds a Templates Hub.
Hindsight 0.5.0 adds a Bank Templates Hub. Browse starter templates, import a manifest to configure any bank, and export setups to reuse across environments.
Adding Persistent Memory to OpenAI Codex with Hindsight
Give OpenAI Codex persistent memory across sessions with Hindsight. Auto-recall injects context before every prompt. Auto-retain extracts facts when sessions end.
One Memory for Every AI Tool I Use
How to wire Claude, ChatGPT, Claude Code, Codex, and OpenClaw to a single shared Hindsight memory bank using Cloudflare Workers as an OAuth 2.1 proxy.
Hindsight Is Now a Native Memory Provider in Hermes Agent
Hermes Agent now supports pluggable memory providers. Here's why Hindsight is the backend to use, and how to set it up in two minutes.
Your OpenClaw Agents Are Strangers to Each Other. Hindsight Changes That.
When you run multiple OpenClaw instances, each one learns independently. Here's how to give every instance in your team a shared memory bank so what one learns, all know.
OpenClaude: Build a Claude Code Agent with Long-Term Memory — and Take It Everywhere
OpenClaude: Build a Claude Code Agent with Long-Term Memory — and Take It Everywhere
Run Hindsight with Ollama: Local AI Memory, No API Keys Needed
Running Hindsight with Ollama gives you a fully local AI memory system. No API keys, no cloud costs, no data leaving your machine. If you want persistent agent memory powered by open-source models on your own hardware, this tutorial walks through the complete setup.