Skip to main content
ClaudeWave

Python SDK + MCP server for Telys — embedded, on-device memory & retrieval for AI assistants. 19-tool MCP surface (io.github.thyn-ai/telys on the Official MCP Registry); the engine is a separate closed, signed on-device runtime — the SDK and MCP surface are Apache-2.0.

MCP ServersOfficial Registry0 stars0 forksPythonApache-2.0Updated today
ClaudeWave Trust Score
95/100
Verified
Passed
  • Open-source license (Apache-2.0)
  • Actively maintained (<30d)
  • Clear description
  • Topics declared
  • Documented (README)
Last scanned: 9/24/2026
Install in Claude Code / Claude Desktop
Method: pip / Python · telys
Claude Code CLI
claude mcp add telys-sdk -- python -m telys
claude_desktop_config.json (Claude Desktop)
{
  "mcpServers": {
    "telys-sdk": {
      "command": "python",
      "args": ["-m", "venv"]
    }
  }
}
1. Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
2. Replace any <placeholder> values with your API keys or paths.
3. Restart Claude. The MCP server and its tools appear automatically.
💡 Install first: pip install telys
Use cases

MCP Servers overview

# telys

<!-- mcp-name: io.github.thyn-ai/telys -->

**Public SDK** for **Telys** — embedded, on-device memory & retrieval. In-process, **zero cloud
roundtrips** at query time.

This package contains the complete developer-facing surface: the `Telys`/`Collection` facades, query/filter
types, the `EmbeddingProvider` interface, the `Tuner`/`TuningPlan` interfaces, the **full MCP server**
(`telys/mcp.py` — 19 tools, protocol 2025-06-18, stdio), a runtime loader, and the `telys` CLI. The
numerical kernel (`libame_kernel`) the tools drive is a separately distributed, signed on-device runtime
fetched by `telys login` (free community license) — the same arrangement as MCP servers that front hosted
or signed-binary backends.

## Install

**As a CLI** (recommended — isolated env, on your PATH, not pinned to one Python):

```bash
pipx install telys

telys login          # sign in → free device license + signed runtime; fully offline thereafter
```

**As a library** (to `import telys` in your own project):

```bash
python -m venv .venv && . .venv/bin/activate
pip install telys
```

> Plain `pip install --user telys` works too, but pip may warn that its user-scripts dir isn't on your
> PATH (a macOS `--user` quirk) — `pipx` avoids that entirely. Runtime platforms: **macOS arm64, Linux
> x86_64/arm64** (Windows: run under **WSL2**).
```python
from telys import Telys
db = Telys("./memory")
col = db.create_collection("docs", dim=768, partition_by="tenant_id")   # dim is arbitrary — 384/768/1024/1536/3072…
col.add(vectors, ids=ids, metadata=metadata)          # bring your own vectors (embedding-agnostic, any dimension)
hits = col.search(qvec, where={"tenant_id": "acme"}, top_k=10, explain=True)
```

The **runtime is required for execution**; the **embedder is optional** — `col.add(vectors, …)` and
`col.add_texts(…)` both need the runtime, but only `*_texts` needs an embedder (bring your own via
`telys.embedding.CallableEmbedder`, or use the on-device bigram embedder).

For local development, install the runtime as a package instead of via the CLI:

```bash
pip install "telys[runtime]"   # or: pip install telys-runtime
```

## MCP server

[![MCP registry](https://img.shields.io/badge/MCP%20registry-io.github.thyn--ai%2Ftelys-blue)](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.thyn-ai/telys)

`telys mcp` runs Telys as a [Model Context Protocol](https://modelcontextprotocol.io) server over stdio,
exposing **19 tools** — the full memory surface (CRUD, filtered queries, lexical search, compaction / IVF /
tuning, plus a repo auto-indexer) — to any MCP client (Claude Desktop/Code, Cursor, Codex, Qwen Code, …).
Everything is local and offline. Introspection (`initialize`/`tools/list`) needs no credentials; executing memory tools requires the one-time free `telys login` (device authorization, free community plan) — fully offline thereafter, no API key in the client config.

```bash
pipx install telys
telys login            # free device license + signed on-device runtime
telys runtime verify   # confirm the runtime the tools drive is present
telys mcp              # serve JSON-RPC 2.0 (protocol 2025-06-18) on stdin/stdout
```

You rarely start it by hand — `telys mcp install` writes the server entry into your clients — or add this
block to a client's MCP config yourself:

```json
{
  "mcpServers": {
    "telys": {
      "command": "telys",
      "args": ["mcp"]
    }
  }
}
```

Registry: [`io.github.thyn-ai/telys`](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.thyn-ai/telys)
on the Official MCP Registry. Server source: [`packages/telys-sdk/telys/mcp.py`](packages/telys-sdk/telys/mcp.py).
MCP docs: [docs.telys.ai/mcp](https://docs.telys.ai/mcp/overview).

| Tool | What it does | Required arguments |
| --- | --- | --- |
| `telys_search` | Semantic + lexical search over a memory collection | `collection`, `query` |
| `telys_add` | Add text documents (collection auto-created if absent) | `collection`, `texts` |
| `telys_create_collection` | Create a collection (fix name + partition key up front) | `name` |
| `telys_list_collections` | List saved collections in the active store | — |
| `telys_stats` | Row counts and index state for one collection | `collection` |
| `telys_upsert` | Add-or-replace rows by id (the idempotent write) | `collection`, `texts`, `ids` |
| `telys_update` | Re-embed/replace EXISTING ids (strict: ids required) | `collection`, `texts`, `ids` |
| `telys_delete` | Tombstone rows by id | `collection`, `ids` |
| `telys_ids` | List live external ids, optionally `where`-scoped | `collection` |
| `telys_count` | Live row count, optionally `where`-scoped | `collection` |
| `telys_get` | Exact row lookup by id (re-reads repo source slices) | `collection`, `ids` |
| `telys_search_lexical` | On-device BM25 keyword search | `collection`, `query` |
| `telys_compact` | Flush tombstones, merge delta into the base layout | `collection` |
| `telys_build_ivf` | Build per-partition IVF indexes (recall-floor calibrated) | `collection` |
| `telys_build_lexical` | Fit the BM25 lexical index | `collection` |
| `telys_tune` | Produce (and optionally apply) a TuningPlan | `collection` |
| `telys_index_repo` | Walk + chunk + ingest a repo, incrementally refreshed | — |
| `telys_repo_search` | Search the auto-indexed repo (re-indexes first, always fresh) | `query` |
| `telys_workspace_info` | Report the configured workspace, repo_id and file count | — |

Every tool ships a rich description (what it does, when to use it, parameters with defaults, failure modes)
and static MCP annotations (`readOnlyHint` / `destructiveHint` / `idempotentHint` / `openWorldHint`) —
`openWorldHint: false` throughout: the server makes no network calls. Listing the tools needs **no
credentials and no runtime**: `initialize` + `tools/list` answer from the static tool registry; only actual
tool calls load the signed runtime lazily.

## Documentation

Full documentation lives at **[docs.telys.ai](https://docs.telys.ai)**:

- [Quickstart: your first collection](https://docs.telys.ai/quickstart-first-collection)
- [Working with data](https://docs.telys.ai/guides/create-a-collection) — add, upsert, search, filter, snapshot
- [Embeddings](https://docs.telys.ai/embeddings/choosing-an-embedder) — built-in lexical + bring-your-own via `CallableEmbedder`
- [CLI reference](https://docs.telys.ai/cli/overview) · [MCP integration](https://docs.telys.ai/mcp/overview) · [Self-hosting](https://docs.telys.ai/serve/overview)
- [SDK API index](https://docs.telys.ai/reference/sdk-api-index)

## Links

- Website: [telys.ai](https://telys.ai) · Pricing: [telys.ai/pricing](https://telys.ai/pricing)
- Account & billing: [accounts.thyn.ai](https://accounts.thyn.ai)
- Docs: [docs.telys.ai](https://docs.telys.ai) · PyPI: [pypi.org/project/telys](https://pypi.org/project/telys)
hacktoberfestllm-toolsmcpmcp-servermemorymodel-context-protocolon-devicepythonretrievalsdk

What people ask about telys-sdk

What is thyn-ai/telys-sdk?

+

thyn-ai/telys-sdk is mcp servers for the Claude AI ecosystem. Python SDK + MCP server for Telys — embedded, on-device memory & retrieval for AI assistants. 19-tool MCP surface (io.github.thyn-ai/telys on the Official MCP Registry); the engine is a separate closed, signed on-device runtime — the SDK and MCP surface are Apache-2.0. It has 0 GitHub stars and its last recorded update is dated 2026-09-24.

How do I install telys-sdk?

+

You can install telys-sdk by cloning the repository (https://github.com/thyn-ai/telys-sdk) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is thyn-ai/telys-sdk safe to use?

+

Our security agent has analyzed thyn-ai/telys-sdk and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains thyn-ai/telys-sdk?

+

thyn-ai/telys-sdk is maintained by thyn-ai. The last recorded GitHub activity is dated 2026-09-24, with 0 open issues.

Are there alternatives to telys-sdk?

+

Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.

Deploy telys-sdk to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Featured on ClaudeWave: thyn-ai/telys-sdk
[![Featured on ClaudeWave](https://claudewave.com/api/badge/thyn-ai-telys-sdk)](https://claudewave.com/repo/thyn-ai-telys-sdk)
<a href="https://claudewave.com/repo/thyn-ai-telys-sdk"><img src="https://claudewave.com/api/badge/thyn-ai-telys-sdk" alt="Featured on ClaudeWave: thyn-ai/telys-sdk" width="320" height="64" /></a>

More MCP Servers

telys-sdk alternatives