vectorshift.ai valid
VectorShift
VectorShift is a platform for building AI pipelines, agents, knowledge bases, and tables. These docs cover three distinct surfaces: the no-code visual platform, the REST API, and the Python SDK. Pick the surface that matches the task and stay within it.
For agents: VectorShift platform for building AI pipelines, agents, knowledge bases and tables; docs cover the no-code builder, REST API and Python SDK.
ai pipelinesai agentsknowledge basespython sdkrest apino-code ai builder
- Authority
- 56 reach 6 · trust 10 · quality 25 · freshness 15
- Tier
- listed
- llms.txt
- https://docs.vectorshift.ai/llms.txt
- llms-full.txt
- https://docs.vectorshift.ai/llms-full.txt
- Sections
- 6
- Links
- 52
- Size
- 6517 bytes
- Popularity rank
- #519798
- Registered
- 2023-06-03
- Country
- United States Hosting inference
- Hosting country
- United States Hosting inference
- Country evidence
- No published address evidence collected yet
- Categories
- Developer tools · AI agents and MCP · AI and machine learning
- For agents
- Interface: a documented API or declared MCP endpoint an agent can call
- Inferred actions
- Read documentation Call an API About these labels
- Audience
- developers · agents can: read docs, call api · en
- First seen
- 2026-10-19T10:43:49.132Z
- Last checked
- 2026-10-25T04:21:35.034Z
- Badge
Their llms.txt
The beginning of the file, from our validated copy saved 2026-10-25T04:21:30.076Z. Cached copy · Source on vectorshift.ai
# VectorShift
> VectorShift is a platform for building AI pipelines, agents, knowledge bases, and tables. These docs cover three distinct surfaces: the no-code visual platform, the REST API, and the Python SDK. Pick the surface that matches the task and stay within it.
## How to use these docs (for AI assistants)
Route by the surface the user is working in. Do not mix surfaces — the SDK, the REST API, and the visual platform have different objects, names, and semantics.
- **Writing Python with the VectorShift SDK** → use **only** pages under `/sdk`. Ignore `/api-reference` and `/platform` — they describe different interfaces and will produce code that does not run.
- **Calling the HTTP/REST API directly** (curl, fetch, non-Python clients) → use **only** pages under `/api-reference`.
- **Building visually / no-code in the platform UI, or understanding what a node does** → use `/platform` and `/nodes`.
- **Account, billing, organizations, subscriptions** → use `/account`.
**Canonical paths:** SDK docs live under `https://docs.vectorshift.ai/sdk/*`. Older `/vectorshift/developers/sdk/*` URLs are stale and permanently redirect to `/sdk/*` — always use and cite the `/sdk/*` form.
When unsure which surface a question is about, ask before answering. Prefer a `reference` page for exact signatures and an `examples` page for full runnable scripts.
## SDK code best practices
When generating VectorShift **Python SDK** code, follow these rules:
- **Authentication:** rely on the `VECTORSHIFT_API_KEY` environment variable. Never hardcode the API key inline (e.g. `vectorshift.api_key = "..."`).
- **Build pipelines with the fluent builder:** `pipeline.add(name="...").llm(...)`. Do not use standalone node constructors (`LlmNode(...)`), and do not pass `nodes=[...]` to the constructor.
- **Make runs idempotent with a fetch-or-create guard at the top**, then build. Nodes dedup by `name`, so a stable `name=` makes re-runs idempotent. Don't pass hardcoded `id=` values.
- **`temperature` is not a top-level `.llm()` argument** (it is silently dropped). Pass it via `sampling=SamplingConfig(temperature=...)`.
- For exact signatures, consult the `/sdk/<primitive>/reference` page; for end-to-end usage, consult the matching `/sdk/<primitive>/examples/*` pages.
## SDK (Python)
- [SDK Overview](https://docs.vectorshift.ai/sdk/index): Build, run, and manage Pipelines, Agents, Knowledge Bases, and Tables from Python.
- [Installation](https://docs.vectorshift.ai/sdk/installation)
- [Quickstart](https://docs.vectorshift.ai/sdk/quickstart): Zero to a running pipeline in 60 seconds.
- [Authentication](https://docs.vectorshift.ai/sdk/authentication)
- [Concepts](https://docs.vectorshift.ai/sdk/concepts): Pipelines, Agents, Sessions, and Knowledge Bases — when to use which.
- [Errors](https://docs.vectorshift.ai/sdk/errors)
- [Pipeline — overview](https://docs.vectorshift.ai/sdk/pipeline/overview) · [reference](https://docs.vectorshift.ai/sdk/pipeline/reference)
- [Agent —
…Related sites
Similar publisher descriptions and documentation. Similarity does not imply affiliation or equivalent capabilities.
| Domain | Title | Category | Country | Authority | llms.txt | llms-full.txt | Save |
|---|---|---|---|---|---|---|---|
| chatbotkit.com | ChatBotKit | interface AI and machine learning AI agents and MCP +2 | US | 56 | ✓ | ||
| zenml.io | ZenML Labs: The Unified AI Platform for Pipelines and Agents | interface AI and machine learning | DE | 56 | ✓ | ✓ | |
| rocketride.org | RocketRide | documentation Developer tools Data and analytics +2 | — | 46 | ✓ | ||
| agno.com | Agno | interface AI agents and MCP Developer tools +1 | US | 60 | ✓ | ✓ | |
| getdynamiq.ai | Dynamiq | interface AI and machine learning AI agents and MCP | US | 55 | ✓ | ✓ | |
| getorchestra.io | Orchestra | interface AI and machine learning Data and analytics +1 | US | 46 | ✓ | ||
| composio.dev | Composio | documentation AI and machine learning AI agents and MCP +1 | — | 64 | ✓ | ✓ | |
| voker.ai | Voker | interface AI and machine learning Data and analytics +1 | US | 52 | ✓ |
Machine-readable: GET /v1/resolve?q=vectorshift.ai · GET /v1/domain/vectorshift.ai · this page as Accept: application/json or text/markdown · MCP lookup_domain
Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.
Own or manage this website?
If you own or manage vectorshift.ai, you can update its listing and review file health, discovery activity and score history.
Manage this listing — optional
What verification unlocks
See how your site is discovered—and control what agents see.
- See your website in the map
Review your indexed topics, nearby publishers sharing headings, measured listing exposure and map snapshots in a private report for your website.
- Control what agents see
Edit your listing description, tags, public contact details and additional llms.txt paths. Publish your terms for automated access, attribution and pricing.
- Make your profile eligible for search
A valid, listed, unblocked, verified profile can appear in our publisher sitemap and become eligible for search-engine visibility. Search engines decide what to index and rank.
- Appear in our llms-full.txt
Eligible verified publishers are listed by name, with their file links and summaries, in the service overview agents can read.
Free. No account registration, backlink or payment required. Public discovery remains available without verification.
Let your coding agent verify it
If your coding agent is authorized to manage this website, paste these instructions into it.
Claim my listing on Agent Web Map for vectorshift.ai:
1. POST https://agentwebmap.com/v1/sites/vectorshift.ai/claims and keep claim_id and claim_secret private.
2. Publish the verification line "AgentWebMap verification: <token>" (token from step 1) in https://vectorshift.ai/llms.txt, or use the DNS, meta-tag or well-known method the response describes. This only verifies the listing; your website and domain remain yours.
3. POST https://agentwebmap.com/v1/sites/vectorshift.ai/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/vectorshift.ai).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verifyCorrections or removal requests: contact the directory.