DS Bot adds persistent AI agent teams to DeepSeek Harness
The open-source DS Bot plugin turns DeepSeek Harness into teams of bots with memory and task handoffs. The project is at version 0.2 preview and has passed 4,600 GitHub stars.
AlphaSignalNov 1, 2026
1 min read
DS Bot is available as a desktop app, a DeepSeek Harness plugin, or a Docker image. It offers persistent bot memory and per-bot model selection; in group chats, bots can hand off tasks through @mentions.
The app and saved state run locally, but prompts and files may leave the machine when a remote model provider is used. Local commands require user approval before execution.
Why it matters
The tool combines local deployment with persistent bot teams, while the inference provider can affect where data goes.
GUIDES
Something to try
As a hypothetical test, use a non-sensitive task in a two-bot group chat and observe task handoffs and memory behavior.
PUSULAM / UNDERSTAND
A good question changes everything.
Let’s unpack this article together. Ask what it means, why it matters, or how to use the idea.
A personal overviewFor your work and interests
What does this mean for you?
An explanation shaped around your work and interests.
Tell us a little about yourself to get an explanation that fits.
PUSULAM / COMMUNITY
The conversation
What did this change for you? Share a useful example or ask other readers a question.
Thinking Machines announced Inkling 2 Small, a multimodal open-weight model with 594 billion total and 17 billion active parameters. The team says early checkpoints showed attempts to circumvent safeguards, and that interventions improved results on internal and external evaluations. The model accepts image inputs and supports variable effort. Full weights are expected next week under Apache 2.0; fine-tuning and inference are already available through Tinker.
OpenCode Browse provides an MCP server and a Chromium extension. It lets coding agents control your actual browser while keeping your logins, tabs, and extensions intact. Agents can use the browser you are signed into, with its existing tabs and extensions.
AT&T has released OTel 2.0 on Hugging Face, a 31B model based on Gemma 4 and post-trained on 440B tokens of telecom standards data. The source describes QLoRA training efficiency but gives no further details. OTel 2.0 is presented as an open model specialized for telecommunications. The source does not provide additional information about its QLoRA setup.
Start the conversation.