# Aleph

> Skill + MCP server to turn your agent into an RLM. Load context, iterate with search/code/think tools, converge on answers.

- **Type:** MCP server
- **Install:** `agentstack add mcp-hmbown-aleph`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Hmbown](https://agentstack.voostack.com/s/hmbown)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Hmbown](https://github.com/Hmbown)
- **Source:** https://github.com/Hmbown/aleph
- **Website:** https://aleph-web.pages.dev/

## Install

```sh
agentstack add mcp-hmbown-aleph
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Aleph

[](LICENSE)
[](https://www.python.org/downloads/)
[](https://pypi.org/project/aleph-rlm/)

Aleph is an [MCP server](https://modelcontextprotocol.io/) and skill for
**Recursive Language Models** (RLMs). It keeps working state — search indexes,
code execution, evidence, recursion — in a Python process outside the prompt
window, so the LLM reasons iteratively over large codebases, long-lived
projects, logs, documents, and data without burning context on raw content.

```text
+-----------------+    tool calls     +-----------------------------+
|   LLM client    | ---------------> |  Aleph (Python process)     |
| (context budget)|  item.value);
const routeKinds = frequency(
  routes.map((route) => (route.includes('.post(') ? 'write' : 'read')),
  2,
);
const notes = await sub_query_map(
  routes.map((route) => `Explain ${route}`),
  routes,
);
({ routeCount: routes.length, routeKinds, notes })
`, context_id="repo")
```

## Safety Model

Aleph is built to keep raw context out of the model window unless you
explicitly pull it back:

- Tool responses are capped and truncated.
- `get_variable("ctx")` is policy-aware and should not be your default path.
- `exec_python` stdout, stderr, and return values are bounded independently.
- `ALEPH_CONTEXT_POLICY=isolated` adds stricter session export/import rules and
  more defensive defaults.
- `ALEPH_ACTION_POLICY=read-only` (or `--action-policy read-only`) keeps action
  tools in read-only mode: search and file loading still work, but writes and
  subprocess execution are blocked.

The safest pattern is always:

1. Load the large context into Aleph memory.
2. Search or compute inside Aleph.
3. Retrieve only the small result you need.

## Docs Map

- [MCP_SETUP.md](MCP_SETUP.md): client-by-client MCP and skill installation.
- [docs/prompts/aleph.md](docs/prompts/aleph.md): the `/aleph` and `$aleph`
  workflow plus tool patterns.
- [docs/CONFIGURATION.md](docs/CONFIGURATION.md): flags, env vars, limits, and
  safety settings.
- [docs/langgraph-rlm-default.md](docs/langgraph-rlm-default.md): LangGraph
  integration with Aleph-style tool usage.
- [examples/langgraph_rlm_repo_improver.py](examples/langgraph_rlm_repo_improver.py):
  repo improvement example with optional LangSmith tracing.
- [CHANGELOG.md](CHANGELOG.md): release history.
- [DEVELOPMENT.md](DEVELOPMENT.md): contributor guide.

## Development

```bash
git clone https://github.com/Hmbown/aleph.git
cd aleph
pip install -e ".[dev,mcp]"
# Optional extras:
#   .[docs]           -> MarkItDown-backed document conversion
#   .[observability]  -> OpenTelemetry spans
pytest tests/ -v
ruff check aleph/ tests/
```

## References

- Zhang, A. L., Kraska, T., Khattab, O. (2025)
  [Recursive Language Models (arXiv:2512.24601)](https://arxiv.org/abs/2512.24601)

## License

MIT

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Hmbown](https://github.com/Hmbown)
- **Source:** [Hmbown/aleph](https://github.com/Hmbown/aleph)
- **License:** MIT
- **Homepage:** https://aleph-web.pages.dev/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** yes
- **Environment & secrets:** no
- **Dynamic code execution:** yes

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-hmbown-aleph
- Seller: https://agentstack.voostack.com/s/hmbown
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.