LM-Kit One
PulseGate's liveness check found it on 15 Sep 2026; it has been in the index since 15 Sep 2026. How this is checked
LM-Kit One is a self-hosted private AI application server deployed on customer-controlled hardware. It supports model serving, agents, search, RAG, document intelligence, and compatibility with OpenAI, Anthropic, Ollama, and MCP clients for developers and organizations.
Inferred · not functionally tested
Overview
6 featuresPurpose: Running AI models and document intelligence privately without sending data to external cloud infrastructure.
Inferred · not functionally tested
Audience: developers and organizations needing private, self-hosted AI infrastructure
Inferred · not functionally tested
Functions: rag, agents, data_extraction
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: unknown · license: Proprietary · platforms: API, CLI, WEB · deployment: browser, cli, self_hosted, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: lm-kit.com. These links do not verify the individual claims.
LM-Kit One sits in PulseGate's Inference & model serving category. Inferred · not functionally tested: It focuses on running AI models and document intelligence privately without sending data to external cloud infrastructure. Inferred · not functionally tested: It is built as a B2B product for developers and organizations needing private, self-hosted AI infrastructure. Basis unknown · not verified: It runs on the web, the command line, and API, and it can be self-hosted.
Behind LM-Kit One is LM-Kit. Inferred · not functionally tested: Among its 6 catalogued features are model serving, agent runtime, and search. Inferred · not functionally tested: Catalogued interfaces include a public API and an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Model serving
- Agent runtime
- Search
- RAG pipelines
- Document intelligence
- OpenAI compatibility
Topics: Inferred · not functionally tested
Built with & integrations
- multiple
- bLangChain in the HTML · bLlamaIndex in the HTML
- local_oss
- bollama in the HTML · bvllm in the HTML · studio in the HTML
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed15 Sep · 15:39 UTCShow HN: LM-Kit One – private AI on your infrastructure seen via Hacker News firehose (Algolia)Source: Hacker News firehose (Algolia) · Open
Frequently asked questions about LM-Kit One
- What does LM-Kit One do?
- Inferred · not functionally tested: LM-Kit One focuses on running AI models and document intelligence privately without sending data to external cloud infrastructure. It is catalogued under Inference & model serving on PulseGate.
- Who should use LM-Kit One?
- Inferred · not functionally tested: LM-Kit One is a B2B product built for developers and organizations needing private, self-hosted AI infrastructure.
- What platforms does LM-Kit One run on?
- Basis unknown · not verified: LM-Kit One runs on the web, the command line, and API. It can also be self-hosted.
- Is LM-Kit One still active?
- PulseGate's liveness check found it on 15 Sep 2026.
- Who makes LM-Kit One?
- LM-Kit One is developed by LM-Kit.
- Does LM-Kit One have an API or integrations?
- Inferred · not functionally tested: Yes — LM-Kit One exposes a public API and an MCP server.
Similar projects
Closest matches by what these projects do