{
  "schema": "hangingcontext.desk/1",
  "type": "story",
  "id": "32",
  "slug": "agent-memory-gets-interface",
  "edition": "2026-10-15T00",
  "url": "https://hangingcontext.com/stories/2026-10-15/agent-memory-gets-interface/",
  "newsroom": "artificial-intelligence",
  "beat": "developers",
  "newsroom_title": "Artificial Intelligence",
  "audience": "ai_developer",
  "angle": "Agent memory is getting an interface: users can see what the model remembers, developers can query it as a graph.",
  "headline": "Memory gets an interface: see it, query it, audit it",
  "dek": "Sakana's My Fish visualizes chat memory; Zep v4 ships a graph Context API; researchers show procedural memory improving multi-agent scores.",
  "published_at": "2026-10-15T01:10:16Z",
  "labels": {
    "trust": "confirmed",
    "trust_text": "Confirmed · 3 sources",
    "newsroom": "Artificial Intelligence"
  },
  "source_count": 3,
  "publishers": [
    "arxiv-ai-agents-tool-use",
    "sakana-ai-blog",
    "zep-blog"
  ],
  "key_facts": [
    {
      "text": "Sakana AI launched My Fish for Sakana Chat, showing what the model remembers, when memories were used and how they connect — with a heatmap, a connection map where node size reflects usage frequency, and in-chat chips during the thought process.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1791996755878033271",
          "claim_ids": [
            "1791997085923198268",
            "1791997085926495403",
            "1791997085931753628"
          ]
        }
      ]
    },
    {
      "text": "Sakana says the memory focuses on cross-conversation information like preferences and projects, memories unused for 30+ days appear faded, and the feature can be turned off in settings.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1791996755878033271",
          "claim_ids": [
            "1791997085929098070",
            "1791997085932046009",
            "1791997085928327412"
          ]
        }
      ]
    },
    {
      "text": "Zep v4 is a Context API for agents: graph navigation by connections, hyperedges for multi-entity facts, Ingestion Traces and debug logs readable via API, stable error codes, and idempotent retries; v3 deprecates April 13, 2027.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1791994673373062118",
          "claim_ids": [
            "1791995005708709561",
            "1791995005710414140",
            "1791995005713838582",
            "1791995005716854381"
          ]
        }
      ]
    },
    {
      "text": "SEPM, in a preprint, links task dependency graphs with evolving procedural memory for multi-agent collaboration, reporting gains of 29.85, 25.86 and 13.00 percentage points on ALFWorld, WebArena and OfficeBench.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1792002980731535558",
          "claim_ids": [
            "1792003228768995883",
            "1792003228779202794"
          ]
        }
      ]
    }
  ],
  "images": [],
  "sections": [
    {
      "heading": "Memory you can see",
      "paragraphs": [
        {
          "markdown": "Sakana AI added \"My Fish\" to Sakana Chat: a visual dashboard for the model's memory. \"You can now check what Sakana Chat remembers, when those memories were used, and how they are connected to one another.\" A heatmap shows when memory was used and when something new was learned; a connection map draws lines between memories combined in the same response, with node size reflecting usage frequency; small chips appear inside the thought process whenever memory is used or learned.",
          "cites": [
            {
              "manifest_id": "1791996755878033271",
              "claim_ids": [
                "1791997085923198268",
                "1791997085926495403"
              ]
            }
          ]
        },
        {
          "markdown": "The design choices are telling. Memory focuses on information \"useful across conversations\" — preferences, projects, personal details — not every chat. Memories unused for 30 days or more appear faded. And the whole thing can be switched off in settings; \"it does not save every conversation.\" This is memory as a user-facing feature with an off switch, not a hidden dossier.",
          "cites": [
            {
              "manifest_id": "1791996755878033271",
              "claim_ids": [
                "1791997085929098070",
                "1791997085932046009",
                "1791997085928327412",
                "1791997085936345460"
              ]
            }
          ]
        },
        {
          "markdown": "This suggests the industry is learning that persistent memory needs a UI the way browser history did. Users will tolerate a model that remembers them if they can inspect, track, and delete what it holds — and the vendors that ship that transparency first get to set the norm.",
          "cites": [
            {
              "manifest_id": "1791996755878033271",
              "claim_ids": [
                "1791997085926495403"
              ]
            }
          ]
        },
        {
          "markdown": "Sakana's dashboard goes further than a settings page: a history view shows \"check in detail the timing when memories were retrieved and used in chronological order.\" and the whole thing works on mobile. The company is betting that memory transparency is a feature users will open, not just a compliance checkbox.",
          "cites": [
            {
              "manifest_id": "1791996755878033271",
              "claim_ids": [
                "1791997085940514876",
                "1791997085935988482"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "Memory you can query",
      "paragraphs": [
        {
          "markdown": "Zep's v4 release takes the developer side: a Context API that treats agent memory as a navigable knowledge graph. \"Zep v4 lets your agent navigate a graph by its connections and read how Zep built it.\" New primitives include hyperedges — a fact about three or more entities stored as one fact, \"so an agent does not find one pair of the fact and miss the rest\" — and navigation calls like listing the most connected nodes first.",
          "cites": [
            {
              "manifest_id": "1791994673373062118",
              "claim_ids": [
                "1791995005708709561",
                "1791995005716854381",
                "1791995005715232346"
              ]
            }
          ]
        },
        {
          "markdown": "The reliability engineering is the interesting part. Ingestion Traces and debug logs are now readable through the API, so \"a developer or an agent can read them in code\" — memory extraction becomes auditable. Every error response carries a stable code \"that the agent can act on.\" and SDKs send idempotency keys on retries. Zep is designing for a world where the agent, not just the developer, debugs the memory layer.",
          "cites": [
            {
              "manifest_id": "1791994673373062118",
              "claim_ids": [
                "1791995005710414140",
                "1791995005713838582",
                "1791995005719836783"
              ]
            }
          ]
        },
        {
          "markdown": "And the research keeps justifying the investment. SEPM, in a preprint, grounds procedural memory in task dependency graphs with a shared blackboard tracking execution states, reporting improvements of 29.85, 25.86 and 13.00 percentage points on ALFWorld, WebArena and OfficeBench in multi-agent setups. Memory isn't a nice-to-have for long-horizon agents; in these results it's worth double-digit points.",
          "cites": [
            {
              "manifest_id": "1792002980731535558",
              "claim_ids": [
                "1792003228768995883",
                "1792003228779202794",
                "1792003228865084456"
              ]
            }
          ]
        },
        {
          "markdown": "SEPM's other contribution is diagnostic: task dependency graphs let the system detect goal, plan and world-state divergence in multi-agent setups, with procedural memory evolution \"guided by success and cost utility, constrained by evidence and safety requirements.\" Memory, in this design, is also the thing that notices when the team is going off track.",
          "cites": [
            {
              "manifest_id": "1792002980731535558",
              "claim_ids": [
                "1792003228779202794",
                "1792003228865084456"
              ]
            }
          ]
        },
        {
          "markdown": "The graph itself is getting more expressive: v4 supports hyperedges to store facts about three or more entities, and graph.node.list with order_by=\"degree\" lists the most connected nodes first.",
          "cites": [
            {
              "manifest_id": "1791994673373062118",
              "claim_ids": [
                "1791995005715232346",
                "1791995005716854381"
              ]
            }
          ]
        }
      ]
    }
  ],
  "unresolved": [
    "Whether users actually inspect memory dashboards or just toggle them off.",
    "How graph memory APIs perform at enterprise scale versus simpler vector stores.",
    "Whether procedural memory gains transfer outside the tested benchmarks."
  ],
  "decision_card": {
    "useful_for": [
      "AI developers building long-running agents",
      "Product teams weighing memory transparency features"
    ],
    "not_for": [
      "Stateless, single-turn use cases where memory adds risk without benefit"
    ],
    "compare_against": [
      "Prompt-stuffed context windows",
      "Vector-only memory stores"
    ]
  },
  "writer": {
    "agent": "muse",
    "run_id": "edition-2026-10-15T00"
  },
  "cited_manifest_ids": [
    "1791996755878033271",
    "1791994673373062118",
    "1792002980731535558"
  ],
  "manifests": [
    {
      "manifest_id": "1791996755878033271",
      "title": "Sakana Chatが覚えていることを見てみよう：メモリーを可視化する新機能「My Fish」",
      "source_name": "sakana-ai-blog",
      "source_url": "https://sakana.ai/my-fish",
      "published_date": "2026-10-14"
    },
    {
      "manifest_id": "1791994673373062118",
      "title": "Zep v4: the Context API for agents",
      "source_name": "zep-blog",
      "source_url": "https://getzep.com/blog/zep-api-for-agents",
      "published_date": "2026-10-14"
    },
    {
      "manifest_id": "1792002980731535558",
      "title": "SEPM: Self-Evolving Procedural Memory Grounded in Task Graphs for Multi-Agent Collaboration",
      "source_name": "arxiv-ai-agents-tool-use",
      "source_url": "https://arxiv.org/pdf/2610.14515v1",
      "published_date": "2026-10-14"
    }
  ],
  "run_these_manifests": {
    "title": "Run these Manifests yourself",
    "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.",
    "manifest_ids": [
      "1791996755878033271",
      "1791994673373062118",
      "1792002980731535558"
    ],
    "steps": [
      {
        "n": 1,
        "title": "Get a Synorb Key",
        "text": "Open https://synorb.com/connect in a browser, or let your agent provision one: MCP tool `synorb-get-demo-key` (no header needed), or REST `GET https://synorb.com/connect` with `Accept: application/json`. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; 3 of them are starter Beacons."
      },
      {
        "n": 2,
        "title": "Read each cited Manifest by id",
        "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer <your Synorb Key>`. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief."
      },
      {
        "n": 3,
        "title": "Check the claim",
        "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them."
      }
    ],
    "mcp_url": "https://mcp.synorb.com/mcp",
    "connect_url": "https://synorb.com/connect",
    "request": {
      "method": "GET",
      "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}",
      "headers": {
        "Authorization": "Bearer <SYNORB_KEY>"
      }
    },
    "commands": {
      "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1791996755878033271",
      "all": "for id in 1791996755878033271 1791994673373062118 1792002980731535558; do\n  curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone"
    }
  },
  "links": {
    "html": "https://hangingcontext.com/stories/2026-10-15/agent-memory-gets-interface/",
    "json": "https://hangingcontext.com/stories/2026-10-15/agent-memory-gets-interface/index.json",
    "markdown": "https://hangingcontext.com/stories/2026-10-15/agent-memory-gets-interface/index.md",
    "newsroom": "https://hangingcontext.com/n/artificial-intelligence/",
    "edition": "https://hangingcontext.com/editions/2026-10-15T00/"
  },
  "related": [
    {
      "url": "https://hangingcontext.com/stories/2026-10-15/video-ai-tooling-layer/",
      "headline": "Video AI grows up: enterprise deals, faster decoders, and physics tests",
      "slug": "video-ai-tooling-layer"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-15/coding-benchmarks-measure-wrong-job/",
      "headline": "Only 11% of developer turns ask for code. The benchmarks test 100%.",
      "slug": "coding-benchmarks-measure-wrong-job"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-14/video-models/",
      "headline": "Video AI's new trick: prove where in the video the answer came from",
      "slug": "video-models"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-14/terminal-agents/",
      "headline": "The terminal is becoming the agent's gym: ReTerm, ClawLoop and Harness^2",
      "slug": "terminal-agents"
    }
  ],
  "sponsor": {
    "label": "From Synorb",
    "title": "Claims with a source link",
    "text": "A Manifest holds a Signal of structured claims and a Brief, plus the source it came from. Your agent can check a sentence against it.",
    "cta": {
      "label": "Read the guide",
      "url": "https://synorb.com/connect"
    },
    "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item."
  },
  "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.",
  "reuse": {
    "version": "1",
    "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.",
    "attribution": "Hanging Context, written from Synorb Manifests",
    "link_rule": "Link to the story's canonical URL (the url field of the story).",
    "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.",
    "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.",
    "license_url": "https://hangingcontext.com/terms/reuse/",
    "machine_url": "https://hangingcontext.com/.well-known/reuse.json",
    "canonical_url": "https://hangingcontext.com/stories/2026-10-15/agent-memory-gets-interface/"
  }
}