toast-harness: Framework and API Interface for Mixedbread's toast-1 Search Agent

Repositorymixedbread-ai/toast-harnessTool

Mixedbread's toast-harness is a Python repository designed for the toast-1 search agent. It allows developers to query the model via an OpenAI-compatible Completions API and provides the open-source agent harness used for training and running retrieval loops with exact token accounting.

Key points

  1. toast-1 Search Agent: A model trained to navigate retrieval tools across document corpora and return ranked chunks, answers, or both.
  2. OpenAI API Compatibility: Integrates via standard OpenAI client libraries using Mixedbread's custom endpoint (api.mixedbread.com/v1) and API key.
  3. Flexible Retrieval Modes: Supports hosted API search tools without local retrieval logic, as well as local custom tools like BM25 and grep.
  4. agent_harness Package: Installable via pip to provide the agent execution loop, tool interfaces, and token accounting for any OpenAI-compatible model.

Why it matters

Iterative, agentic retrieval often requires complex orchestrations. Specialized search agents like toast-1 package multi-round tool interactions into simple API calls or modular loops, lowering the barrier to deploying advanced search workflows.

Analysis

The project solves the complexity of building multi-step retrieval loops by offering both a managed API workflow and an open-source harness (agent_harness). Built in Python under the Apache-2.0 license, it targets AI engineers and developers designing agentic search or RAG systems. With 33 stars and 7 forks, it is an early-stage tool despite recent development.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:Mixedbread Team

    Mixedbread Launches Specialised Search Agent Toast 1

    Mixedbread has announced Toast 1, a specialised search and retrieval agent designed to handle query decomposition, evidence gathering, and context curation as a standalone model or subagent for frontier LLMs.

    AI & LLMs· Announcement

  • Link:Mixedbread

    Mixedbread: Integrated Retrieval Platform for AI Agents

    Mixedbread is an end-to-end data retrieval platform designed for AI agents. Rather than requiring developers to wire together standalone parsers, vector stores, and rerankers, it bundles multimodal embeddings, a native multi-vector database, and a dedicated search agent.

    AI & LLMs· Tool

  • Link:primeintellect.ai

    Mixedbread Trains Toast 1 Deep-Search Agent Using Prime-RL

    A case study by Prime Intellect outlines how Mixedbread trained Toast 1 using Prime-RL and Verifiers v1. Fine-tuned from Qwen3.6-35B-A3B, the retrieval subagent matches frontier-level context gathering 12 times faster and at significantly lower cost.

    AI & LLMs· Resource

  • Repository:deepseek-ai/deepseek-harness

    DeepSeek Harness: Plugin-Based Open-Source AI Agent Framework

    DeepSeek Harness (dsh) is an open-source AI agent harness by DeepSeek AI. Built with TypeScript and Cordis, it uses an 'everything-is-a-plugin' architecture to provide modular agent capabilities and a Web UI.

    212.8kstarsTypeScript

    AI & LLMs· Tool

  • Repository:xerj-org/xerj

    XERJ: Rust-based search engine for AI agents and RAG

    XERJ is a Rust-based search engine designed as an alternative to Elasticsearch and grep for AI workflows. It provides zero-config auto-indexing for code, documentation, logs, and PDFs, aiming to significantly cut token usage for AI agents handling search, RAG, and memory tasks.

    7.9kstarsRust

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.