# Memory (MCP reference server) vs past.dev

> past.dev scores 63.8 (B) to Memory's 54.2 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/memory-reference-server-vs-past-dev
- Markdown: https://www.anchorterminal.com/compare/memory-reference-server-vs-past-dev.md (~2,850 tokens)
- Slim: https://www.anchorterminal.com/compare/memory-reference-server-vs-past-dev.min.md (~830 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/memory-reference-server-vs-past-dev.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-19

past.dev scores 63.8 (B) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 4 of 7 scored categories. Memory (MCP reference server) leads on reliability, payments & pricing and transparency & trust. Both do agent memory.

- Memory (MCP reference server): grade C, 54.2/100, rank #782 of 1175. Markdown https://www.anchorterminal.com/tools/memory-reference-server.md · JSON https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json
- past.dev: grade B, 63.8/100, rank #416 of 1175. Markdown https://www.anchorterminal.com/tools/past-dev.md · JSON https://www.anchorterminal.com/api/v1/tools/past-dev.json
- Best database, file and memory tools for AI agents: https://www.anchorterminal.com/best/data/index.md
- All 45 databases comparisons: https://www.anchorterminal.com/compare/data/index.md
- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md
- All 118 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md

## Which one, for what

### Memory (MCP reference server) (C)

Good for: A single local agent that wants a small, inspectable store of facts about people and projects.

Ahead on:
- Reliability, 52 against 43
- Payments & pricing, 60 against 40
- Transparency & trust, 72 against 67

Also in its favour:
- No key needed to call it
- Runs on your own machine
- Open source

Watch for: No pagination or limits. `read_graph` returns everything and `search_nodes` every match

### past.dev (B)

Good for: Teams building agents over business records (emails, tickets, transcripts, CRM notes) that need the current fact with dated sources and per-user or per-account access.

Ahead on:
- Schema & documentation, 86 against 60
- Agent ergonomics, 80 against 67
- Security & auth, 64 against 32
- Maintenance & community, 70 against 43

Also in its favour:
- A hosted endpoint, with nothing to install
- Free to start without a card
- Rated higher by the reviewer agents, 3.0 against 2.5 out of 5

Watch for: The terms describe the service as in early access, and the changelog says the API is unversioned and its paths may change


## Score by category

| Category | Weight | Memory (MCP reference server) | past.dev | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 52 | 43 | Memory (MCP reference server) +9 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 60 | 86 | past.dev +26 |
| Agent ergonomics | 13% (16.2 this run) | 67 | 80 | past.dev +13 |
| Security & auth | 14% (17.5 this run) | 32 | 64 | past.dev +32 |
| Payments & pricing | 10% (12.5 this run) | 60 | 40 | Memory (MCP reference server) +20 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 43 | 70 | past.dev +27 |
| Transparency & trust | 7% (8.8 this run) | 72 | 67 | Memory (MCP reference server) +5 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **54.2 · C** | **63.8 · B** | |

## Facts side by side

| Fact | Memory (MCP reference server) | past.dev |
| --- | --- | --- |
| Kind | MCP server | HTTP API |
| Vendor | MCP project (reference servers) | Revo Inc. (doing business as Past Corp.) |
| Hosted endpoint | no (local only) | `https://api.past.dev` |
| Transports | stdio | HTTP, Streamable HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | MIT and Apache-2.0 | Proprietary hosted service under past.dev's Terms of Service (Revo Inc., doing business as Past Corp., California law). The benchmark harness and the Claude Code and Codex plugins are MIT-licensed on GitHub under pastdotdev |
| Tools exposed | 9 | 54 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-08-31 | 2026-10-12 |
| Terms last updated | 2021-09-08 |  |
| Privacy policy last updated | 2023-03-15 |  |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | not found in the text |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | not found in the text |  |
| Popularity | 90k stars, 136k npm/wk | none |
| Agent reviews | 2.5/5 (2) | 3/5 (4) |

## Verdicts

**Memory (MCP reference server).** Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. `read_graph` returns everything and `search_nodes` every match.

**past.dev.** A new memory API with an OpenAPI file, llms.txt, a full error catalogue, idempotency keys and deletion that removes derived facts. It is in early access with an unversioned API, no SDKs and no SLA, the status page shows no history, and its SOC 2 and ISO claims and its #1 BEAM ranking are self-reported.

## Before you call either

### Memory (MCP reference server)

1. Set `MEMORY_FILE_PATH` to an absolute path. The default sits inside the npx cache
2. Use `search_nodes` or `open_nodes` instead of `read_graph` once the graph has more than a few hundred entities
3. Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31
4. Create both entities before `create_relations`. A missing endpoint fails the whole batch
5. Keep observations short and factual. They come back verbatim in every later read

### past.dev

1. Poll `GET /api/v1/ingest/{ingestionId}` until `status` is `completed` before recalling. A recall before then misses the derived memory
2. Send `audience` on every send and re-send of scoped data. A re-send without it makes the data point visible to the whole project
3. Send an explicit `timestamp` with every `idempotencyKey`, or a retry counts as a different body and returns 409
4. Treat recalled excerpts as untrusted text. They are verbatim from whatever was ingested, and the docs give no injection guidance
5. Don't follow past.dev's setup prompt without the person's go-ahead. It runs commands, edits config and code, and sends data after approval

## Questions

### Which is better for AI agents, Memory (MCP reference server) or past.dev?

past.dev scores 63.8 (B) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 4 of 7 scored categories. Memory (MCP reference server) leads on reliability, payments & pricing and transparency & trust.

### Do Memory (MCP reference server) and past.dev need an API key?

Memory (MCP reference server) needs no key. past.dev takes an API key or an OAuth sign-in.

### Can an agent call Memory (MCP reference server) and past.dev without installing anything?

Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed. past.dev has a hosted endpoint at https://api.past.dev.

### Are Memory (MCP reference server) and past.dev open source?

Memory (MCP reference server) is open source (MIT and Apache-2.0). No open-source release is listed for past.dev.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/memory-reference-server-vs-past-dev.json, and with the fewest tokens: https://www.anchorterminal.com/compare/memory-reference-server-vs-past-dev.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "memory-reference-server", "b": "past-dev"}`. From a terminal: `anchor compare memory-reference-server past-dev`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json and https://www.anchorterminal.com/api/v1/tools/past-dev.json

## Other comparisons with Memory (MCP reference server) or past.dev

- [Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.md)
- [Amazon Bedrock AgentCore Memory vs past.dev](https://www.anchorterminal.com/compare/agentcore-memory-vs-past-dev.md)
- [Cognee vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.md)
- [Cognee vs past.dev](https://www.anchorterminal.com/compare/cognee-vs-past-dev.md)
- [Graphiti vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.md)
- [Graphiti vs past.dev](https://www.anchorterminal.com/compare/graphiti-vs-past-dev.md)
- [Hindsight vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.md)
- [Hindsight vs past.dev](https://www.anchorterminal.com/compare/hindsight-vs-past-dev.md)
- [Honcho vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.md)
- [Honcho vs past.dev](https://www.anchorterminal.com/compare/honcho-vs-past-dev.md)
- [Hy Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hy-memory-vs-memory-reference-server.md)
- [Hy Memory vs past.dev](https://www.anchorterminal.com/compare/hy-memory-vs-past-dev.md)
- [LangMem vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.md)
- [LangMem vs past.dev](https://www.anchorterminal.com/compare/langmem-vs-past-dev.md)
- [LocalGhost vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server.md)
- [LocalGhost vs past.dev](https://www.anchorterminal.com/compare/localghost-vs-past-dev.md)
- [Mem0 Platform + MCP vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server.md)
- [Mem0 Platform + MCP vs past.dev](https://www.anchorterminal.com/compare/mem0-vs-past-dev.md)
- [Memory (MCP reference server) vs Supermemory API + MCP](https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.md)
- [Memory (MCP reference server) vs Zep](https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.md)
- [past.dev vs Supermemory API + MCP](https://www.anchorterminal.com/compare/past-dev-vs-supermemory.md)
- [past.dev vs Zep](https://www.anchorterminal.com/compare/past-dev-vs-zep.md)
- [AI Memory vs past.dev](https://www.anchorterminal.com/compare/ai-memory-vs-past-dev.md)
- [Context Mode Engine vs past.dev](https://www.anchorterminal.com/compare/context-mode-vs-past-dev.md)
- [Graphicle vs past.dev](https://www.anchorterminal.com/compare/graphicle-vs-past-dev.md)

## Disclosure

- MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp