Skip to content
UsecaseBoard
Saved0
← All use cases
huggingfaceopen-model

inclusionAI Ling-3.1-flash: 560B MIT hybrid MoE for agents and coding

At a glance

inclusionAI/Ant Ling open-sourced Ling-3.1-flash (560B total / ~25B active, 1M context, MIT) for agents, office, search, and SWE—day-0 SGLang/vLLM recipes, tool/reasoning parsers, and strong Terminal-Bench / SWE-bench Pro / SkillsBench numbers; works in Claude Code, Hermes, OpenClaw, and related harnesses. This workflow is listed under open-model, coding-agents, MoE, MIT, tool-calling.

Agents / tools
Ling-3.1-flash, SGLang, vLLM, Claude Code, Hermes Agent

Building a tool for these workflows? Sponsor / inquire.

Save ideas in this browser. Upvotes count across the board.

Prompt excerpt

Pull lmsysorg/sglang:dev-ling-3.1-flash, launch with TP/EP and NEXTN speculative decoding, then point Claude Code or Hermes at the OpenAI-compatible endpoint with enable_thinking true.

Related workflows

Explore all →
blogopen-weights

Reflection Beam 1.0: 501B open-weight agentic coding model

US lab Reflection open-sourced Beam (501B MoE / 23B active, 1M context, Apache 2.0) for coding and long-horizon agents, with day-0 vLLM/SGLang/Transformers support, Mirror CLI harness, and 40+ inference partners including OpenRouter and Ollama.

Beam 1.0Mirror CLIvLLM+3
Source ↗
blogmodel-release

Meta Muse Spark Open: 816B open-weight agentic coding model

Oct 15 open weights: multimodal MoE (816B total / 42B active, 1M context) trained for long-horizon coding agents—plan, tool-call, self-correct—with Muse Code demos shipping real iOS changes on-device; HF + API hosts.

Muse Spark OpenMuse CodeHugging Face+3
Source ↗
huggingfaceopen-model

Tencent Hy-Memory-30B-A3B: open long-term memory writer for agents

Tencent Hunyuan open-weights Hy-Memory-30B-A3B (~3B active MoE) to replace the general LLM on the write path of Mem0/MemOS/Hy-Memory—trained with on-policy distillation + attributed memory RL; beats Claude Opus 5 / DeepSeek V4.1 Flash on a fixed cross-harness memory-writer matrix; Apache-friendly HF weights + GitHub framework.

Hy-Memory-30B-A3BMem0MemOS+2
Source ↗
docscoding-agents

fzf + tmux: complete paths and hashes inside Claude Code / Codex prompts

junegunn (fzf author) documents how shell CTRL-T bindings die once you live in an agent prompt—and how tmux PREFIX bindings restore fzf: tmux-fzf-complete (files/dirs/URLs/on-screen paths/sentences) and fzf-git.sh (commits, branches, PRs) inject selections as keystrokes into Claude Code or Codex. Requires tmux 3.7+ floating panes and agent settings that keep scrollback (/tui default for Claude Code; Codex alternate_screen=never). Pattern: make agent prompts as completable as the shell.

fzftmux-fzf-completefzf-git.sh+3
Source ↗