tldw

Spec sheet

Purpose

tldw is an open-source, self-hosted research system for ingesting, transcribing, searching, and querying source material.Read 7 Oct 2026 · tldwproject.com

Deployment

The site documents Docker single-user, Docker multi-user with Postgres, and local single-user setup paths.Read 7 Oct 2026 · tldwproject.com

API

The project provides OpenAI-compatible Chat, Audio, Embeddings, and Evals APIs.Read 7 Oct 2026 · tldwproject.com

Integrations

The site lists hosted model providers including OpenAI, Anthropic, Google, Cohere, DeepSeek, Groq, Mistral, OpenRouter, HuggingFace, and Qwen, plus local options including Ollama, vLLM, and llama.cpp.Read 7 Oct 2026 · tldwproject.com

Security

The v0.1.31 release notes describe hardening for authentication and authorization, outbound scraping policy, audit durability, and workspace-bounded MCP command execution.Read 7 Oct 2026 · tldwproject.com

Privacy

The site says data stays on infrastructure users control and that tldw has no telemetry, analytics, or phone-home behavior.Read 7 Oct 2026 · tldwproject.com

APIs and automation

The project provides OpenAI-compatible Chat, Audio, Embeddings, and Evals APIs, plus MCP tool execution and metrics.Read 7 Oct 2026 · tldwproject.com

Automation

MCP automation includes workspace-bounded command execution, policy-aware discovery, and approval gates.Read 7 Oct 2026 · tldwproject.com

Availability

The project is labeled beta, and the site says PyPI installation is not generally available yet.Read 7 Oct 2026 · tldwproject.com

Community support

The site directs users to Discord, Zulip, and GitHub for discussion, help, and contribution.Read 7 Oct 2026 · tldwproject.com

Data handling

The site says users keep data on infrastructure they control, with no telemetry, analytics, or phone-home behavior.Read 7 Oct 2026 · tldwproject.com

Installation limit

The site says PyPI installation is not generally available yet and directs users to install from a repository checkout.Read 7 Oct 2026 · tldwproject.com

Model integrations

It supports hosted model providers including OpenAI, Anthropic, Google, Cohere, Groq, Mistral, and OpenRouter, as well as local options such as Ollama, llama.cpp, and vLLM.Read 7 Oct 2026 · tldwproject.com

Models

It supports local inference, hosted model APIs, or both through one interface.Read 7 Oct 2026 · tldwproject.com

Project status

The site labels the current release v0.1.31 beta and says it is usable now for people comfortable with a beta project.Read 7 Oct 2026 · tldwproject.com

Search

Hybrid retrieval searches across transcripts, notes, and documents using full-text search, vectors, and reranking.Read 7 Oct 2026 · tldwproject.com

Study tools

The v0.1.31 beta includes Study Packs, flashcard templates, study suggestions, and a recipe-based evaluation framework.Read 7 Oct 2026 · tldwproject.com

Support and community

The site directs users to Discord and Zulip for community discussion and help.Read 7 Oct 2026 · tldwproject.com

Supported content

It accepts video, audio, PDFs, web pages, EPUB, DOCX, Markdown, XML, and other inputs.Read 7 Oct 2026 · tldwproject.com

Supported inputs

It accepts video, audio, PDFs, web pages, EPUB, DOCX, Markdown, XML, and other formats.Read 7 Oct 2026 · tldwproject.com

Transcription

It converts recordings into searchable text that can be quoted, summarized, and reused.Read 7 Oct 2026 · tldwproject.com

Transcription and retrieval

It turns recordings into searchable text and uses hybrid retrieval across transcripts, notes, and documents.Read 7 Oct 2026 · tldwproject.com

Workspace

Notes, prompts, chats, artifacts, and source material can live in the same system.Read 7 Oct 2026 · tldwproject.com

Workspace features

It includes notes, prompts, chatbooks, study packs, flashcard templates, study suggestions, and evaluation workflows.Read 7 Oct 2026 · tldwproject.com

Where Specifiction places it

• AI Video Summarizers#21 of 257.3