Skip to main content
Glama
README.md
<div align="center">

<img src="web/logo-300w.png" alt="emem logo" width="64">

<h1>Search the physical world.<br>Every answer is signed.</h1>

<p><b>Ask emem about any place, field, river, forest, building or machine. It reads open sensors and models, computes the answer, and returns it with its source, its method and a signature anyone can check offline. One MCP URL, no key.</b></p>

[![Install in VS Code](https://img.shields.io/badge/VS%20Code-Install%20emem-0098FF?logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=emem&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Femem.dev%2Fmcp%22%7D)
[![Claude plugin](https://img.shields.io/badge/Claude-plugin-D97757)](plugins/emem/)
[![ChatGPT](https://img.shields.io/badge/ChatGPT-emem-10a37f?logo=openai&logoColor=white)](https://chatgpt.com/plugins/plugin_asdk_app_6a6a0832a59081918b19aec0ddf9ec77)
[![GitHub MCP Registry](https://img.shields.io/badge/GitHub%20MCP%20Registry-io.github.Vortx--AI%2Femem-181717?logo=github&logoColor=white)](https://github.com/mcp/Vortx-AI/emem)

[![ci](https://github.com/Vortx-AI/emem/actions/workflows/ci.yml/badge.svg)](https://github.com/Vortx-AI/emem/actions/workflows/ci.yml)
[![PyPI](https://img.shields.io/pypi/v/ememdev?label=pypi%20ememdev)](https://pypi.org/project/ememdev/)
[![npm](https://img.shields.io/npm/v/@vortxai/emem?label=npm%20%40vortxai%2Femem)](https://www.npmjs.com/package/@vortxai/emem)
[![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](./LICENSE)

</div>

## Try it: one question, no key

```bash
curl -s -X POST https://emem.dev/v1/ask -H 'content-type: application/json' \
  -d '{"q":"What is the air quality in Delhi right now?"}' \
  | jq '{answer: (.answer | split("\n")[0]), limits: .direct_answer.limits, fact: .direct_answer.fact_cid, signed_facts: (.receipt.fact_cids | length)}'
```

What came back on 20 November 2026, in 2.3 s:

```json
{
  "answer": "PM2.5 at Delhi: PM2.5 69.80 ug/m^3, on a reading dated 2026-11-20 (today).",
  "limits": [
    "Delhi covers more than one cell. This is the reading at the one cell the name resolves to, not a value over the whole place.",
    "CAMS is a model analysis on a coarse grid, not a street-level monitor."
  ],
  "fact": "olew2lwppg4uazm4sgiiv56qv4p4owphfon3ijqb3bvkqb35lyua",
  "signed_facts": 49
}
```

The answer names its source and says what it cannot tell you. Every fact behind it is signed, and the fact id resolves, for you or any other agent, to the same bytes.

The same for one farm field, from the latest clear Sentinel-2 pass:

```bash
curl -s -X POST https://emem.dev/v1/recall -H 'content-type: application/json' \
  -d '{"lat":30.745,"lng":75.605,"bands":["indices.ndvi"]}' \
  | jq '.facts[0] | {value, observed_at, scene: .derivation.args[2], surface: .surface_class.label, token: .memory_token}'
```

On 20 November that gave NDVI 0.169 from scene `S2B_MSIL2A_20261117T054109_R005_T43REQ`, with the pixel read as bare soil: a field between the rice harvest and the wheat.

## Web search and emem

| | Web search | emem |
|---|---|---|
| Returns | pages that mention the place | a measured value at the place |
| Source | whoever wrote the page | the sensor or model reading, named |
| Freshness | when it was crawled | read on demand from the latest pass or model run |
| Trust | rank | a signature, an append-only log, and a check anyone can run |
| For an agent | text to paraphrase | a value and a token to cite |
| When nothing is known | more pages | a signed absence that says where it looked |

## Connect your agent

```bash
claude mcp add --transport http emem https://emem.dev/mcp     # Claude Code
```

Any MCP host takes the same URL, `https://emem.dev/mcp`: Claude Desktop, ChatGPT, Cursor, VS Code, Cline and Gemini CLI. The Claude Code plugin adds nineteen skills on top: `/plugin marketplace add Vortx-AI/emem`, then `/plugin install emem@emem`. In code: `pip install ememdev` or `npm i @vortxai/emem`.

**For agents.** Connect to `https://emem.dev/mcp`. It advertises the 18 tools of the core loop in one page, about 75 KB of context, not the whole catalog: loading all 119 descriptors costs about 329 KB. For the lightest first contact, `emem_tools` returns the loop and a menu in about 13 KB, and `tools/call` dispatches every tool by name, with or without its `emem_` prefix. To hand records on, prefer a bundle: `emem_memory_bundle` names up to 256 facts in 38 characters.

Then ask in plain words. Each prompt below runs one tool:

| Ask your agent | What emem reads | Tool |
|---|---|---|
| "What is the air quality here right now?" | CAMS analysis: PM2.5, NO2 and ozone | `emem_air` |
| "Will it rain here this week?" | met.no forecast: temperature, cloud, rain and wind (ERA5 past hours through `emem_recall`) | `emem_weather` |
| "Is there open water here, and how often?" | JRC surface-water history since 1984 and Sentinel-1 radar, which sees water through cloud | `emem_water` |
| "Show the NDVI of this field through the last kharif season" | every clear Sentinel-2 pass in one call, each date with its pixel count (4.2 s for a 4.4 ha field, 13 dates) | `emem_field_series` |
| "Draw the field boundaries in this 1 km box" | Fields of The World outlines with net area and, if asked, the 10 m pixels each field holds | `emem_field_boundaries` |
| "Is this cocoa plot deforestation-free under the EUDR?" | the EU forest map and forest loss after 31 December 2020, one signed check per plot | `emem_eudr_dds` |
| "Was there tree-cover loss here since 2020?" | Hansen tree cover and year of loss, ESA WorldCover land class | `emem_forest` |
| "How steep is this slope? What is the soil?" | Copernicus DEM slope and ruggedness, SoilGrids organic carbon and texture | `emem_terrain`, `emem_soil` |
| "How many buildings and roads are in this block?" | Overture buildings, places and road length | `emem_recall` |
| "Read this scanned lab report" | Tesseract OCR, with a receipt that binds the image, the text and the engine | `emem_ocr` |
| "Did this robot run what it says it ran?" | its signed execution trace, checked segment by segment | `emem_trace_verify` |
| "Check the numbers in my draft before I send it" | each cited token resolves, and its value is compared with your sentence | `emem_guard_verdict` |

117 wired measurements from open sources, read on demand. The full list: [emem.dev/tools](https://emem.dev/tools).

## Why the answers hold up

- **Every number traces to its source:** the satellite scene, the band, the method and the registry version are in the record.
- **Nothing changes quietly:** records go into an append-only log ([RFC 6962](https://emem.dev/v1/log/sth)) that two independent operators co-sign. When we find a fault we correct it in the open with a signed erratum.
- **Anyone can check it without us:** each receipt verifies offline (`pip install "ememdev[signing]"`, then `verify_receipt_offline`), or paste a token at [emem.dev/verify](https://emem.dev/verify).
- **Gaps are stated, not filled:** where nothing qualifies, a signed absence says where emem looked and why. Cautions (cloud, a field too small for its pixels) travel with the value.

The long form, with what each record promises and how each promise is checked, is in [docs/settlement.md](docs/settlement.md).

## Choose your path

| You are | Start here |
|---|---|
| Trying it | the command above, or `https://emem.dev/mcp` in any MCP host. Reads need no key. |
| Building an agent or app | [agent guide](https://emem.dev/agents.md), [OpenAPI](https://emem.dev/openapi.json), [examples](examples/) for LangChain, LlamaIndex, CrewAI, AutoGen, Agno and Mastra |
| A compliance or agri team | [EUDR evidence, plot by plot](https://emem.dev/eudr), [crop intelligence](https://emem.dev/agriculture), or [open an issue](https://github.com/Vortx-AI/emem/issues) to talk to us |
| Running your own node | `docker run -p 127.0.0.1:5051:5051 ghcr.io/vortx-ai/emem:latest`, then [docs/self-host.md](docs/self-host.md); an air-gapped build is in [emem-airgap](crates/emem-airgap/README.md) |

## Numbers

119 MCP tools · 177 registered algorithms · 117 wired measurements from open sources, satellites and weather models to buildings and soil · a transparency log of 3.39 million entries co-signed by 2 independent operators · Apache-2.0, pure Rust, runs as one binary.

## Who builds on it

- **[eudr.dev](https://eudr.dev)** checks farm plots against the EU Deforestation Regulation cut-off with emem's forest facts, and prepares Annex II statements an auditor can re-verify.
- **[geo.qa](https://geo.qa)** runs a second node, whose transparency-log head emem co-signs.

## Use it where you already work

| | |
|---|---|
| **In a chat** | the [emem app in ChatGPT](https://chatgpt.com/plugins/plugin_asdk_app_6a6a0832a59081918b19aec0ddf9ec77) (mention `@emem`), and emem in the Claude directory |
| **In Claude Code** | the [plugin](plugins/emem/), the MCP server plus nineteen skills: `/plugin marketplace add Vortx-AI/emem`, then `/plugin install emem@emem` |
| **In an IDE or MCP host** | Claude Desktop, Cursor, Cline, VS Code and Copilot, Gemini CLI (`gemini extensions install https://github.com/Vortx-AI/emem`), all on one endpoint, `https://emem.dev/mcp` |
| **In a workflow tool** | the verified [Dify plugin](https://marketplace.dify.ai/plugin/vortx-ai/emem) |
| **In code** | the [Python](https://pypi.org/project/ememdev/) and [TypeScript](https://www.npmjs.com/package/@vortxai/emem) clients, REST ([OpenAPI](https://emem.dev/openapi.json)), and [examples](examples/) for LangChain, LlamaIndex, CrewAI, AutoGen, Agno and Mastra |
| **Agent to agent** | [A2A](https://emem.dev/a2a): read the [agent card](https://emem.dev/.well-known/agent-card.json), send a task, verify the signed result |

Per-host configs, and every directory emem is listed in, are on [the reference page](https://emem.dev/reference#client-setup). Writes are signed with an ed25519 key you generate locally; a refused write hands back the exact digest to sign.

## Run it yourself

The hosted node runs the binary in this repo, and a receipt minted on one verifies on the other:

```bash
docker run -p 127.0.0.1:5051:5051 ghcr.io/vortx-ai/emem:latest
```

Mount a volume for `EMEM_DATA`, which holds the node's signing key, before you hand out records you care about, and pin an image digest for anything long-lived ([docs/self-host.md](docs/self-host.md)).

For a machine with no route out, such as a payload computer in orbit, [`emem-airgap`](crates/emem-airgap/README.md) takes custody of files in one directory and writes signed records to another, and `emem-encode` captures the execution evidence it can. Each record says which of the two guarantees it carries. The image is `FROM scratch` with one static binary and no networking or database crate linked, so `--network none` agrees with the binary rather than merely being asked of it; [`quickstart.sh`](crates/emem-airgap/quickstart.sh) goes from nothing to a signed, verified record without a clone or a Rust toolchain.

Independent witnesses co-sign the log head, listed live at [`/v1/log/witnesses`](https://emem.dev/v1/log/witnesses), so a split view is detectable. Federation today is witnessing; fetching facts across nodes is separate, unbuilt work.

## What the checks do not prove

- **A signature says who, never that it is true.** A receipt proves what one responder signed. Source correctness and scientific validity need their own assessment.
- **A token points at bytes held somewhere.** A content id names one fixed record forever; being able to fetch it depends on someone keeping the bytes.
- **A place name resolves to one 10 m cell.** Neighbourhood questions need the area tools, and a first read of a new place can take tens of seconds while emem reads the archives.
- **Time series are sparse.** At one warm cell geo.qa measured 38 NDVI readings over three years, about 12.7 a year: enough for a direction, not for a full phenology curve.
- **One responder signs, not a network.** A receipt never claims consensus.
- **Notes are public and permanent.** Encoding a file never uploads it; publishing a note does. Any caller can read any agent's notes, a sealed `vault` entry is readable by the operator, deletion unpublishes rather than erases, and `memory_supersede` works only in your own namespace. Encrypt client-side for anything private ([PRIVACY.md](PRIVACY.md#agent-written-memory)).

Version 2.4.6, a patch on the 2.4.0 minor. The receipt preimage last changed in 2.0.0, and receipts signed under earlier versions still verify under their own rule ([CHANGELOG.md](CHANGELOG.md)). Next: [docs/roadmap.md](docs/roadmap.md).

## Learn more

| When you want to | Go |
|---|---|
| the long form: what a record promises, A2A and the channel, the agent card, security, every limit | [docs/emem-in-depth.md](docs/emem-in-depth.md) |
| why it matters: robot fleets, satellite tasking, agent swarms, compaction | [emem in depth, what breaks without it](docs/emem-in-depth.md#what-breaks-without-it) |
| see it work in ten minutes | [tutorial](docs/tutorials/first-verified-memory.md), [agent walkthroughs](examples/agent-walkthroughs.md) |
| follow one request end to end, with live consoles | [emem.dev/how-it-works](https://emem.dev/how-it-works) |
| wire your agent in | [agent guide](https://emem.dev/agents.md), [skills](https://emem.dev/skills.md), [connect a client](https://emem.dev/reference#client-setup) |
| put it on a machine | [machines that ask emem where they are](docs/robots.md), [emem-airgap](crates/emem-airgap/README.md), [federation](docs/federation.md) |
| check the trust model, formally | [whitepaper](https://emem.dev/whitepaper), [protocol](docs/protocol.md), [formal model](docs/model.md), [security](docs/security.md), [verifier spec](https://emem.dev/v1/verifier_spec) |
| read the full API | [/openapi.json](https://emem.dev/openapi.json), [/mcp/full](https://emem.dev/mcp/full), [all tools](https://emem.dev/tools), the [wire spec](https://emem.dev/spec.md) |
| use it for evals, and what is unmeasured | [benchmarks with methods](docs/benchmarks.md), [how emem compares](docs/how-emem-compares.md), [roadmap](docs/roadmap.md) |

## Citation

Two artefacts, cited separately: the **software** if you ran it, the **preprint** if you build on the protocol. GitHub's *Cite this repository* button reads [CITATION.cff](CITATION.cff), which carries both.

```bibtex
@software{emem_software,
  title     = {emem: shared, verifiable memory for AI agents},
  author    = {Kumari, Jaya and Singh, Avijeet},
  year      = {2026},
  version   = {2.4.6},
  url       = {https://github.com/Vortx-AI/emem},
  license   = {Apache-2.0},
  publisher = {Vortx AI Private Limited}
}

@misc{emem2026,
  title     = {emem: A research on Content-Addressed, Verifiable Earth-Memory
               Protocol for AI Agents over Foundation-Model Embeddings},
  author    = {Kumari, Jaya and Singh, Avijeet},
  year      = {2026},
  doi       = {10.5281/zenodo.20706893},
  publisher = {Zenodo}
}
```

The preprint is open (CC-BY-4.0) and not yet peer-reviewed.

## Contributing and license

Issues and pull requests welcome: [CONTRIBUTING.md](CONTRIBUTING.md), [SECURITY.md](SECURITY.md). Pure Rust, Apache-2.0 ([LICENSE](LICENSE), [NOTICE](NOTICE)). Default data sources are open, with no API keys and no lock-in. A shared memory is worth more the more agents read and write it; if yours use emem, a star helps other builders find it.

## Content address

Every section above this one is a unit of one signed tree: `emem:tree:omu3zfjzvpb65jn6f44ux452ey`, root `cjijxfeat7eftjkitxi4inilopfwhaj5l6v3nz4pveelydnd2mka`, published under the key `k572x7go`. A single section is `emem:tree:omu3zfjzvpb65jn6f44ux452ey#row=<i>`, so another agent can cite one part of this file and anyone can prove it was in the file as published:

```bash
curl -s "https://emem.dev/memories/by_attester/k572x7go/readme/tree-20261120d.md" > index.md
curl -s "https://emem.dev/v1/tree/omu3zfjzvpb65jn6f44ux452ey?row=3" > row.json
python3 tools/verifiers/emem-tokenise-files/tree_proof.py check row.json index.md README.md
```

`index.md` is the signed note at [`/memories/by_attester/k572x7go/readme/tree-20261120d.md`](https://emem.dev/memories/by_attester/k572x7go/readme/tree-20261120d.md). `python3 scripts/readme_tree_check.py` rebuilds the whole tree from this file and compares its root with the index, and CI runs it, so a README edited without re-signing fails the build. The tree changes whenever the README does, and this section is left out of it because it names the tree.

TDQS

A4.1/5.0

Scored across 18 tools

Disambiguation3/5

The core lifecycle tools are distinct, but several boundaries overlap: emem_ask, search, fetch and emem_recall all retrieve signed facts, while fetch and emem_memory_token_resolve both dereference fact citations. emem_intent and emem_tools are meta-wrappers that can route to the same operations, so descriptions help but do not eliminate misselection risk.

Naming Consistency4/5

Most tools use a predictable emem_ snake_case prefix, and the names are readable despite mixing noun- and verb-oriented forms. The two unprefixed tools, search and fetch, are clear exceptions that slightly break the pattern.

Tool Count3/5

Eighteen tools is heavy for a listed MCP surface, especially when it includes both primitive operations and multiple high-level wrappers such as emem_ask, emem_intent and emem_tools. The breadth is justified by the domain, but the set feels borderline over-scoped rather than tightly curated.

Completeness3/5

The citation lifecycle is well covered: locate, recall, mint tokens, bundle, resolve, verify and guard. However, the listed surface omits several primitives explicitly referenced by the descriptions, such as trajectory, polygon recall, diff, edges and inferences, so agents may hit dead ends unless they can access /mcp/full.

Maintenance

ActivityActive
ResponsivenessUsually handled