Blog·Learning

Push, Pull, or Poll? Choosing an Agent Memory Ingestion Pattern

By Shardul Mane·2 min read

Push, Pull, or Poll? Choosing an Agent Memory Ingestion Pattern

Choose ingestion patterns from freshness needs, source capabilities, and recovery requirements. Push delivers change notifications, polling discovers changes on a schedule, and on-demand pull fetches information when a task needs it. Many reliable integrations combine them.

A webhook does not guarantee complete delivery, and a periodic sync does not guarantee current answers. The application needs an accepted-version rule and a way to repair missed changes.

Use push for prompt change notification

An event can tell the connector that a record changed. Validate the event, retain its identity, and decide whether to trust its payload or fetch the authoritative current record. Retries and duplicate delivery should not create unrelated copies.

Do not assume events arrive in source order. An older event delivered late must not overwrite a newer revision. Keep a source revision or equivalent ordering field when the source supplies one.

Use polling for reconciliation

A cursor-based sync can recover changes missed during downtime. Commit the cursor only after the corresponding records have reached the connector's defined durable checkpoint. Otherwise, a crash can advance the cursor past work that never completed.

Track deletions and permission changes, not only new content. If the source's change feed omits some events, plan a periodic reconciliation that can find missing or inaccessible records without reimporting everything blindly.

Use on-demand pull for volatile authority

Some facts should be fetched from their owning system at answer time, such as current order status or access rights. A remembered summary can identify what to ask for, but it should not replace the authoritative lookup when freshness is essential.

Account for the latency and failure path. If the source is unavailable, say the current status could not be verified rather than presenting old memory as current fact.

Combine the patterns around one record identity

A webhook, a scheduled sync, and an on-demand fetch may encounter the same source. Map all three to a stable source ID and version rule. Record which path supplied each accepted revision so problems remain traceable.

For call-based sources, include the full audio-to-memory cost ledger when comparing ingestion patterns.

The ingestion architecture guide covers the downstream lifecycle. For supported services, review Supermemory's connectors and start with one test source. Verify a duplicate event, a missed event, and a permission change before enabling a broad sync.

  1. An update to supermemoryWe've discontinued the supermemory company brain and Nova. Everyone who was charged has been refunded, our MCP and plugins continue to run, and we're going all in on the memory engine.News
  2. Scaling Conversations: How Adapta Grew Usage Without Losing ContextAdapta added Supermemory as a persistent memory layer so every conversation keeps its context — letting the team scale usage without losing the thread.Case Study
  3. How Chatarmin Ditched RAG and Went Memory-Only with SupermemoryChatarmin replaced a heavy RAG pipeline with Supermemory's memory layer — cutting average AI response time from 40s to 12s and token usage by 40–50%.Case Study
  4. SMFS: making agentic retrieval 55% cheaper AND more accurateWe launched SMFS.ai (Supermemory Filesystem) a few weeks ago, with a simple bet: We can redesign the filesystem specifically for agents, with special files, structures, and commands that it can use for it's tasks. Today, SMFS is used by hundreds of companies to power their agents.Engineering
  5. Introducing Dynamic Dreaming: supermemory now connects the dots, for you.Dreaming is magical. TLDR: We're launching Dynamic Dreaming in supermemory today, which automatically works if you're using supermemory in any way - API, OpenClaw, Hermes agent, etc.Engineering
  6. Dear reader, we just made supermemory insanely cheap... the Context CloudWhen I first started building supermemory, I had one goal: To build the best memory system for AI. I would talk to customers, and find out that memory was not the only thing they needed - They were all setting up 7-8 different vendors at the same time.Engineering
  7. Introducing @supermemory/tools v2.0.0Today we're releasing v2.0.0. This release unifies the API across all agents sdk integrations from AI SDK to Mastra, makes conversation identity a first-class concept, and ships with memory saving on by default.Engineering
  8. Solving the Precision-Recall Tradeoff: Search Result AggregationWhen you're building memory for AI, search is your foundational layer. The way search generally works is straightforward: the user defines a query, and then sets a limit (top-K) on how many search results they want returned. Usually, this is set to 10 or 20.Engineering
  9. Stateful Coding Agents with Memory: Build Long-Running Agents (2026)We built a plugin for Claude Code and OpenCode that gives your coding agent persistent memory. It remembers your preferences, learns your codebase, and never loses context mid-conversation. The result is an agent you can run for months without starting over.Engineering
  10. OpenClaw Memory Problems: Why It Forgets and How to Fix It (2026)TLDR: Today, we are releasing a new version of our openclaw plugin - https://github.com/supermemoryai/openclaw-supermemory. This post is going to be a bit technical, so bear with me (or bookmark for later!) In this post, I will talk about what we do about OpenClaw memory, and how we fix it.Engineering
  11. Clawd / Molt bot's memory SUCKS. We gave it supermemory.I'm the founder of supermemory. Clawd/Molt bot is blowing up right now, with many, many use cases. I set it up, too, and have been using it through telegram. TLDR: just go to https://supermemory.ai/docs/integrations/clawdbot to set up supermemory for your clawd bot.Engineering
  12. Catch up with our UNFORGETTABLE Launch WeekOver the last year, one belief has guided almost everything we’ve built at Supermemory AI becomes meaningfully useful only when it remembers. Memory shouldn’t be something developers rebuild from scratch. It shouldn’t be fragile, expensive, or trapped inside a single tool.News
  13. Empowering the Next Generation of Founders: Supermemory Startup ProgramIf there’s one thing we’ve learned while building Supermemory, it’s that most startups don’t fail because they didn't build features; they fail when infrastructure slows them down, or they built too slow.News
  14. Building code-chunk: AST Aware Code ChunkingAt Supermemory, we're building context engineering infrastructure for AI. A huge part of that is dealing with code: ingesting repos, understanding structure, and making it searchable. The problem is that most code chunking solutions are terrible. We built code-chunk to fix this.Engineering
  15. Supermemory raises $3 million with the best memory engine for LLMsToday, I am excited to announce our first funding round to accelerate our mission of building an interoperable, scalable and reliable memory for LLMs and agents. Memory is one of the hardest challenges in AI right now.News
  16. Mem0 vs Supermemory: Why Scira SwitchedScira AI moved its production memory layer from Mem0 to Supermemory. This is what failed, what improved, and how the team evaluated the two systems.Case Study
  17. Never Record Again: How Montra Uses Supermemory to Rethink Video CreationCampbell Baron, the founder of Montra, has been making videos since he was twelve. By thirteen, he was already doing brand work. Today, he’s betting on a very different future for creators: a world where recording is the exception, and most videos are generated from scratch.Case Study
  18. Unified Memory That Works Where You Work: Your Second Brain With SupermemoryHi everyone, I’m Dhravya, the founder of Supermemory. I want to start with a little story behind why this product means so much to me. You can also skip straight to what it is and how it works below.Engineering
  19. Supermemory just got faster on PlanetScaleWhat is Supermemory? Supermemory completes the missing part of the LLM puzzle: memory. Just as memory is crucial for human intelligence, it's essential for truly intelligent AI systems.Engineering
  20. Faster, smarter, reliable infinite chat: Supermemory IS context engineering.People are obsessed with prompts and prompt engineering. Sure, what you say is important, but what the model knows when you say it is the difference between a stateless text generator and an intelligent AI system. In short, context is the most crucial component.News
  21. We solved AI API interoperabilityOne API to rule them all, One spec to find them, One library to bring them all and in the TypeScript, bind them. When we were building the the Infinite Chat API, initially, we only supported the OpenAI format. This was fine, until a lot of our customers started asking, asking for more.Engineering
  22. The Wow Factor of Memory - How Flow Used Supermemory To Build Smarter, Stickier ProductsOverview: Flow is a note-taking app built around a bold vision: to create a more personal, context-aware writing experience powered by AI. At the heart of this mission is memory.Case Study
  23. The UX and technicalities of awesome MCPsLast month, we launched the Supermemory MCP, mostly to test our own infrastructure and get some initial traction. It blew up. To my absolute surprise, the initial launch itself got half a million impressions (!!!). Then, we launched and got #2 on ProductHunt too.Engineering
  24. Architecting a memory engine inspired by the human brainLanguage is at the heart of intelligence, but what truly powers meaningful interaction is memory — the ability to accumulate, recall, and contextualize information over time. Large Language Models (LLMs) have mastered language, but memory remains their Achilles’ heel.Engineering