{
  "listings": [
    {
      "slug": "ai-memory",
      "name": "AI Memory",
      "company": "Fabio Akita",
      "grade": "B",
      "fit": "yes",
      "why": "Lifecycle hooks for Claude Code, Codex, Cursor and twenty other harnesses capture sessions, memory_briefing and memory_recent summarise without an LLM, SessionStart sends the handoff, and the wiki lives in the server data directory, not the repository.",
      "source": "https://raw.githubusercontent.com/akitaonrails/ai-memory/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/ai-memory"
    },
    {
      "slug": "basic-memory",
      "name": "Basic Memory",
      "company": "Basic Memory LLC",
      "grade": "A",
      "fit": "yes",
      "why": "The Claude Code and Codex plugins run SessionStart with a bounded context brief and PreCompact checkpoints, capture goes to ~/.basic-memory/inbox not the repository, and bm_read fetches a note by path or permalink.",
      "source": "https://docs.basicmemory.com/raw/integrations/harness-capture.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/basic-memory"
    },
    {
      "slug": "hindsight",
      "name": "Hindsight",
      "company": "Vectorize, Inc.",
      "grade": "D",
      "fit": "yes",
      "why": "npx @vectorize-io/hindsight-coding-agents install claude-code adds three hooks, an MCP server and a skill for a per-repo bank, sessions start from a summary of architecture and in-flight work, and uninstall removes precisely what install added.",
      "source": "https://hindsight.vectorize.io/sdks/integrations/coding-agents",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/hindsight"
    },
    {
      "slug": "claude-mem",
      "name": "claude-mem",
      "company": "Alex Newman",
      "grade": "C",
      "fit": "caveat",
      "why": "Hooks capture every tool use, SessionStart injects the project's recent observations and get_observations fetches cited ids; but the observer queue was lost on restart (issue 4068) and folder CLAUDE.md files, once written everywhere, are now off by default.",
      "source": "https://docs.claude-mem.ai/architecture/hooks.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/claude-mem"
    },
    {
      "slug": "cognee",
      "name": "Cognee",
      "company": "Topoteretes UG (haftungsbeschränkt)",
      "grade": "D",
      "fit": "caveat",
      "why": "MCP serves Claude Code, Cursor and Codex with agent-scoped datasets and a code graph, but there are no capture hooks or session summaries; the agent must call remember itself.",
      "source": "https://docs.cognee.ai/cognee-mcp/mcp-overview.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cognee"
    },
    {
      "slug": "context-mode",
      "name": "Context Mode Engine",
      "company": "MKSF LTD",
      "grade": "C",
      "fit": "caveat",
      "why": "Hooks log prompts, edits, commands and errors per project into ~/.context-mode, Claude Code and Codex get a state block of at most 2,048 B at SessionStart, and ctx_resume(seq) returns any row; the block is a log of this machine's sessions, not extracted decisions.",
      "source": "https://contextmode.ai/docs/engine/long-sessions.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/context-mode"
    },
    {
      "slug": "everos",
      "name": "EverOS",
      "company": "Evermind AI, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "The MCP server reaches Claude Code, Codex and Cursor with an autonomy protocol and a Claude Code plugin saves and recalls sessions, but the agent track is extracted by LLM and the plugin page was not read.",
      "source": "https://github.com/EverMind-AI/EverOS/blob/main/docs/mcp.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/everos"
    },
    {
      "slug": "graphicle",
      "name": "Graphicle",
      "company": "KarLex AI, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "connect --hooks stores Claude Code and Codex turns as sources and session start gets one line, recall_project takes a token budget and read_project_source continues a cited excerpt; but proposed memories wait for review, and setup writes .claude/settings.local.json and Git hooks into the folder.",
      "source": "https://github.com/Graphicle-AI/graphicle/blob/main/docs/mcp.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/graphicle"
    },
    {
      "slug": "honcho",
      "name": "Honcho",
      "company": "Plastic Labs, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "The Claude Code plugin captures through hooks, injects directives, summary and peer card at session start, and redacts secrets; but the memory is about the person across all projects by design, so project isolation is not the model.",
      "source": "https://honcho.dev/docs/v3/guides/integrations/claude-code.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/honcho"
    },
    {
      "slug": "hy-memory",
      "name": "Hy Memory",
      "company": "Tencent",
      "grade": "C",
      "fit": "caveat",
      "why": "The coding scene stores facts, experiences and a diff chain from tool-call traces isolated by user_id, workspace_id and branch, and source tags separate Cursor, Codex and OpenClaw; capture hooks exist only as Hermes and OpenClaw plugins, none for Claude Code.",
      "source": "https://github.com/Tencent-Hunyuan/Hy-Memory/blob/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/hy-memory"
    },
    {
      "slug": "mem0",
      "name": "Mem0 Platform + MCP",
      "company": "Embedchain, Inc. (DBA Mem0)",
      "grade": "E",
      "fit": "caveat",
      "why": "The Claude Code plugin captures through hooks, extracts in the background every five exchanges, recalls up to five memories by repo or directory scope and redacts prompts; it needs a Mem0 Platform key, which free accounts must back with their own LLM key after 30 days.",
      "source": "https://docs.mem0.ai/integrations/claude-code.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mem0"
    },
    {
      "slug": "memmachine",
      "name": "MemMachine",
      "company": "MemVerge, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Claude Code connects over MCP with add_memory and search_memory and an OpenClaw plugin exists, but no session capture hooks or summary were found in the pages read.",
      "source": "https://docs.memmachine.ai/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/memmachine"
    },
    {
      "slug": "memori",
      "name": "Memori",
      "company": "Memori Labs Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "A Claude Code skill and memori_recall_summary and memori_compaction restore state across sessions, but the skill fires recall on nearly every turn (listing weakness) and project isolation depends on a process id header.",
      "source": "https://memorilabs.ai/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/memori"
    },
    {
      "slug": "mempalace",
      "name": "MemPalace",
      "company": "MemPalace (open-source project)",
      "grade": "B",
      "fit": "caveat",
      "why": "Stop and PreCompact hooks for Claude Code and Codex tell the AI to file memories and mine imports ~/.claude/projects by wing; but the Stop hook blocks the AI to save, and an upgrade made the palace read as empty until migrate shipped (issue 469).",
      "source": "https://mempalaceofficial.com/guide/hooks.html",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mempalace"
    },
    {
      "slug": "supermemory",
      "name": "Supermemory API + MCP",
      "company": "Supermemory",
      "grade": "C",
      "fit": "caveat",
      "why": "The Supermemory MCP gives Claude Code and Cursor add_memory, search_memory and get_profile over shared spaces, but no hooks or automatic session capture were found; the agents page covers API integration only.",
      "source": "https://supermemory.ai/docs/supermemory-mcp/mcp.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/supermemory"
    },
    {
      "slug": "tencentdb-agent-memory",
      "name": "TencentDB Agent Memory",
      "company": "Tencent",
      "grade": "C",
      "fit": "caveat",
      "why": "The proxy records every proxied turn through session/add and injects memory, wiki and code graph into Claude Code, Codex and OpenClaw requests; but session/add is not idempotent, stores all turns, and recall is keyword search with time filters.",
      "source": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/feat/server_team/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/tencentdb-agent-memory"
    },
    {
      "slug": "tokenrip",
      "name": "Tokenrip",
      "company": "Quintel, LLC",
      "grade": "B",
      "fit": "caveat",
      "why": "workspace_load returns bounded context, workspace_sessions lists who worked and each step's why, pins hold up to 20 decisions and tasks carry handoffs; but nothing captures a session automatically.",
      "source": "https://tokenrip.com/mcp",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/tokenrip"
    },
    {
      "slug": "zep",
      "name": "Zep",
      "company": "Zep Software, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "The Zep Context plugin and Context MCP Server give Claude Code, Codex and Cursor add_memory and search_graph on the user's own graph, but sign-in runs through Google Workspace or an Enterprise IdP, so a headless agent cannot use it, and nothing captures sessions.",
      "source": "https://help.getzep.com/v4/context-mcp-server.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/zep"
    },
    {
      "slug": "past-dev",
      "name": "past.dev",
      "company": "Revo Inc.",
      "grade": "BB",
      "fit": "unchecked",
      "why": "Coding-agent plugins are listed but their pages were not read.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/past-dev"
    },
    {
      "slug": "agentcore-memory",
      "name": "Amazon Bedrock AgentCore Memory",
      "company": "Amazon Web Services, Inc. (regional AWS entities by account location)",
      "grade": "A",
      "fit": "no",
      "why": "No hooks or install for Claude Code, Codex or Cursor; events are written by the application through CreateEvent.",
      "source": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/agentcore-memory"
    },
    {
      "slug": "egoist-ai-passport",
      "name": "Egoist AI Passport",
      "company": "Egoist Machines, Inc.",
      "grade": "C",
      "fit": "no",
      "why": "No coding-agent hooks or session capture; the product carries personal memory between assistants.",
      "source": "https://ego.ist/llms.mdx/agents",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/egoist-ai-passport"
    },
    {
      "slug": "google-memory-bank",
      "name": "Agent Platform Memory Bank",
      "company": "Google LLC",
      "grade": "B",
      "fit": "no",
      "why": "No hooks or coding-agent integration; memories come from Agent Platform sessions or direct content.",
      "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/scale/memory-bank",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/google-memory-bank"
    },
    {
      "slug": "graphiti",
      "name": "Graphiti",
      "company": "Zep Software, Inc.",
      "grade": "D",
      "fit": "no",
      "why": "No hooks or session capture; the MCP server is a general memory graph the agent writes to with add_memory.",
      "source": "https://github.com/getzep/graphiti/blob/main/mcp_server/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/graphiti"
    },
    {
      "slug": "langmem",
      "name": "LangMem",
      "company": "LangChain (the licence file gives no legal form)",
      "grade": "D",
      "fit": "no",
      "why": "No hooks or session capture; a LangGraph library for agents the team builds.",
      "source": "https://langchain-ai.github.io/langmem/background_quickstart/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/langmem"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 8,
    "after": [
      "coding-agents.session-start",
      "code-search.repo-context"
    ],
    "area": "agent-runtime",
    "asks": [
      "what did we decide about the auth module last time",
      "pick up where we left off",
      "don't re-read the whole repo again"
    ],
    "before": [
      "coding-agents.session-end"
    ],
    "blockers": [
      "observer queue held only in process memory, lost on restart (claude-mem #4068)",
      "upgrade changes the on-disk format and the store reads as empty (MemPalace #469)",
      "setup uploads recent prompts to a cloud without asking (claude-mem 15.2.0 to 15.8.3)",
      "proposed memories wait for a person to approve them (Graphicle)"
    ],
    "capabilities": [
      "memory.store",
      "memory.search",
      "memory.capture-hooks"
    ],
    "category": "agent-memory",
    "categoryName": "Agent memory",
    "checked": "2026-11-12",
    "companies": {
      "fit": 3,
      "fitWithLimit": 14,
      "tagged": 30
    },
    "competition": "few",
    "fits": [
      "ai-memory",
      "basic-memory",
      "hindsight"
    ],
    "fitsWithLimit": [
      "claude-mem",
      "cognee",
      "context-mode",
      "everos",
      "graphicle",
      "honcho",
      "hy-memory",
      "mem0",
      "memmachine",
      "memori",
      "mempalace",
      "supermemory",
      "tencentdb-agent-memory",
      "tokenrip",
      "zep"
    ],
    "id": "agent-memory.coding-session-memory",
    "listings": {
      "caveat": 15,
      "no": 5,
      "notRead": 0,
      "tagged": 32,
      "unchecked": 1,
      "yes": 3
    },
    "name": "Carry a coding agent's context from one session to the next",
    "status": "draft",
    "success": "At the start of a new session the agent gets a summary of the last sessions' decisions and can fetch a cited observation by id in one more call; nothing from another project appears; the hooks do not write files into the repository unasked. Measured: the summary is under 2,000 tokens.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/agent-memory.coding-session-memory.json",
    "weight": 20,
    "weightBasis": "8 of 36 accounts; the HN 'Stop Claude Code from forgetting' thread (225 comments) and the claude-mem, MemPalace and Basic Memory issues"
  }
}
