Carry a coding agent's context from one session to the next
Two or three companies' docs show a full fit.
What counts as done
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, for our own tests: the summary is under 2,000 tokens. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: what did we decide about the auth module last time
, pick up where we left off
, don't re-read the whole repo again
Does the job 3
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| AI Memory B Fabio Akita | 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 |
| Basic Memory A Basic Memory LLC | 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 |
| Hindsight D Vectorize, Inc. | 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 |
Does the job, with a limit 15
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| claude-mem C Alex Newman | 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 |
| Cognee D Topoteretes UG (haftungsbeschränkt) | 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 |
| Context Mode Engine C MKSF LTD | 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 |
| EverOS BB Evermind AI, Inc. | 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 |
| Graphicle BB KarLex AI, Inc. | 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 |
| Honcho B Plastic Labs, Inc. | 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 |
| Hy Memory C Tencent | 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 |
| Mem0 Platform + MCP E Embedchain, Inc. (DBA Mem0) | 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 |
| MemMachine C MemVerge, Inc. | 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 |
| Memori D Memori Labs Inc. | 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 |
| MemPalace B MemPalace (open-source project) | 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 |
| Supermemory API + MCP C Supermemory | 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 |
| TencentDB Agent Memory C Tencent | 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 |
| Tokenrip B Quintel, LLC | 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 |
| Zep BB Zep Software, Inc. | 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 |
Couldn't check 1
The docs were closed to us, or silent. These carry no mark either way.
| Listing | Why |
|---|---|
| past.dev BB Revo Inc. | Coding-agent plugins are listed but their pages were not read. |
Doesn't do this job 5
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Amazon Bedrock AgentCore Memory A Amazon Web Services, Inc. (regional AWS entities by account location) | No hooks or install for Claude Code, Codex or Cursor; events are written by the application through CreateEvent. source |
| Egoist AI Passport C Egoist Machines, Inc. | No coding-agent hooks or session capture; the product carries personal memory between assistants. source |
| Agent Platform Memory Bank B Google LLC | No hooks or coding-agent integration; memories come from Agent Platform sessions or direct content. source |
| Graphiti D Zep Software, Inc. | No hooks or session capture; the MCP server is a general memory graph the agent writes to with add_memory. source |
| LangMem D LangChain (the licence file gives no legal form) | No hooks or session capture; a LangGraph library for agents the team builds. source |
What stops agents finishing
- 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)
Around it
Before: coding-agents.session-end. After: coding-agents.session-start, code-search.repo-context.
Where this comes from
Weight 20 of 100 in Agent memory: 8 of 36 accounts; the HN 'Stop Claude Code from forgetting' thread (225 comments) and the claude-mem, MemPalace and Basic Memory issues
The same as data: /api/v1/use-cases/agent-memory.coding-session-memory.json, or the MCP tool get_use_case with id agent-memory.coding-session-memory. Other jobs in this category: /api/v1/niches?category=agent-memory.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.