Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

DeepSeek Harness

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 5

  1. DeepSeek merges Harness, Web, App and Platform teams into a product department

    Citing a report by The Paper, Chinese outlets say DeepSeek has merged its Harness team with its Web, App and Platform teams into a single “product department” responsible for all of the company's product, design and R&D work, with former Harness lead Cui Tianyi heading it; Cui confirmed the report to The Paper. DeepSeek Harness is a TypeScript agent runtime framework DeepSeek open-sourced in August 2026 under the MIT license, built around an “everything is a plugin” design in which models, tools, sessions, sandboxes, storage and the agent loop are all supplied through the Cordis plugin system; its v0.2 desktop preview shipped on September 29 with ready-to-use macOS and Windows installers. The report also says the new department is hiring product designers and designers.

    IT之家 AI · 🔥 23
  2. What Is an Agent Harness? The Scaffolding Around LLMs, Explained

    According to a DeveDigest report, the term "Agent Harness" has become a buzzword in AI development after DeepSeek released an open-source desktop client called DeepSeek Harness and OpenAI launched an Agents API at its developer conference. The article explains that the model supplies only reasoning, while the harness is the surrounding system — execution loop, tool calling, context and memory management, sandbox permissions and replayable logs — that lets an agent actually finish real work. It cites testing by data analytics company Databricks finding that the same model plugged into different coding-agent harnesses can differ by more than 2x in per-task cost with no change in task quality, partly because a harness's system prompts and tool declarations consume tokens.

    DoNews · 🔥 6
  3. DeepSeek-V4.1-Flash: 552B multimodal MoE with 1M context

    DeepSeek published DeepSeek-V4.1-Flash on Hugging Face, a natively multimodal mixture-of-experts model with 552B backbone parameters and up to a 1M-token context, built on a Causal Encoder-Decoder design (20 encoder plus 20 decoder layers) that activates only 8B parameters per token in prefill and 16B in decode. It combines Compressed Sparse Attention 2 with FP4 main-KV caching (E2M1 format, one E4M3 scale per 16 channels) to cut the global KV cache to about 890 bytes per token — roughly a quarter of DeepSeek-V4-Flash — and offers a continuously controllable reasoning effort from 1 to 100, with weights under the MIT license. The vendor's own model card reports Terminal-Bench 2.1 at 90.6 (versus Opus-5.0 at 89.1 and GPT-5.6 Sol at 88.8), DeepSWE v1.1 at 74.2 and a Codeforces rating of 3471, but these figures are self-reported and not independently verified; the release also omits a Jinja chat template and ships a deepseek-recipe toolkit for prompt encoding instead.

    DeepSeek · Hugging Face · 🔥 3
  4. Community plugin DS Bot turns DeepSeek Harness into a bot system

    A community plugin called DeepSeek Bot (DS Bot) has appeared for DeepSeek Harness (DSH), turning the harness into a bot system that reportedly supports a long-lived bot team, with a main bot, bots messaging each other and group chats. The project explicitly states it is an independent community effort and not an official DeepSeek product. The sources say DS Bot ships with a main bot already configured on first open, but full capabilities and limitations are not detailed.

    量子位（原生 RSS） · 🔥 0
  5. Uber open-sources ADR agentic AI detection and response system

    Uber has open-sourced ADR (Agentic AI Detection and Response), an enterprise security system for AI agents that is deployed in production at the company. The repository includes ADR Discovery, ADR Sensor, ADR-Bench and ADR Detector, which inventory AI apps, CLI agents, IDE extensions, local model runtimes and MCP servers on endpoints, and capture agent intent, tool use and execution traces from 7+ coding tools including Claude Code, Cursor, Codex, GitHub Copilot CLI, DeepSeek Harness, opencode, Claude Desktop and Gemini CLI. The project says ADR-Bench spans 304 tasks and 134 MCP servers across all 17 agent attack techniques; the ADR Prevention component and the ADR Explorer engine are not part of the open-source release, and an accompanying paper was accepted to MLSys 2026.

    GitHub Trending · Python · 🔥 0

Experience and discussion from the community

Share my DeepSeek Harness experienceAsk about DeepSeek Harness

Nobody has shared their experience with DeepSeek Harness yet.