2026年10月20日 技术热点总结

项目简介：Debloat any Android or Google TV over Wi-Fi and get an Apple TV-style home.

技术栈：Java、adb、adblock、android-tv、android-tv-launcher、apple-tv、bloatware-removal、claude-code、debloat

核心介绍：cleanyour.tv · The prompt · 54 TV lists · 12 built on it · The tweet Strip the bloatware from any Android TV or Google TV over Wi-Fi, and replace the ad-filled home screen with a clean launcher that looks like an Apple TV. No root, no cable, nothing uninstalled, and a one-line restore if you change your mind. 54 TVs with tested lists

项目数据：⭐ 5,158 Stars，🍴 620 Forks

技术栈：C

核心介绍：> Use your AI assistant to help you build the Mac app. We recommend Claude Code, Codex, or any other AI assistant you prefer. English | 中文 > **Every shader in the shared list is ready before you play.

项目数据：⭐ 1,684 Stars，🍴 268 Forks

项目简介：Ears for coding agents: let AI hear, review and make sound. CPU-only, open source.

技术栈：Python、ai-agents、audio、claude-code、mcp、sound-design

核心介绍：Watch the 22 s launch film – every sound in it was made in code by earshot forge; no recordings, no music track. AI coding agents can now write the code that renders a film, a product demo or a game. They still cannot hear what they made. They cannot tell a premium key press from a cheap one, notice that a hit lands 80 ms after the cut, or hear that the music swells in the wrong place.

项目数据：⭐ 1,513 Stars，🍴 90 Forks

项目简介：One 8 KB skill that replaces REA (Reverse Engineer Anything): plain CLI tools, no MCP. Benchmarked: 38% faster, 35% cheaper.

技术栈：Python

核心介绍：REA (Reverse Engineer Anything) puts an MCP layer between your agent and tools it can already use: asar, otool, nm, go version -m, jadx, apktool, Ghidra, tshark, binwalk, sqlite3. leanrea drops that layer. It tells the agent which command is fastest for each kind of target, gives it ready-to-paste recon commands, and lists the traps that REA’s code handles for you. The agent then runs the real tools itself.

项目数据：⭐ 991 Stars，🍴 14…

技术栈：Python

核心介绍：Hy Memory Production-grade dual-system cognitive memory for LLM agents. English | 中文

项目数据：⭐ 958 Stars，🍴 79 Forks

项目简介：AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with OpenAI, ChatGPT, Claude, Gemini, Ollama, OpenCode. Blender AI addon and plugin, copilot for 3D, bpy Python scripting, MCP integration.

技术栈：Python、ai-assistant、blender、blender-addon、blender-ai、blender-automation、blender-extension、blender-mcp、blender-plugin

核心介绍：Download · Getting started · Connections and agents Start with an idea. Ask the assistant to inspect your scene, create a product-display layout, arrange objects, assign materials or prepare an export. Follow its act…

We seek a hierarchical resolution of residual error under a composite learning objective as a principled mechanism for identifying and exploiting additional information, particularly under distribution shift and perturbation. Inspired by the System 1/System 2 paradigm, we formulate this principle as a two-loop mechanism serving a common inference goal. A fast, System 1-like loop resolves the residual addressable by the available evidence; the remaining epistemic residual triggers a medium speed, System 2-like loop that actively acquires additional evidence and measures its informational val…

Comparing financial disclosures across languages requires identifying shared accounting concepts and recovering all numerical facts that express them. Existing benchmarks evaluate aspects of these capabilities, but provide limited insight into whether both succeed on the same multilingual evidence. In particular, it remains unclear whether language models can recognize these concepts across languages and exhaustively recover their corresponding numerical evidence from the same contexts. We introduce MULTIFINGROUND, a benchmark designed to investigate this recognition-grounding gap in multil…

Whole-body tracking has become the interface through which operators drive humanoid robots, yet the references it consumes are recorded on level ground and carrying nothing, so the tracker is aware of neither the forces the robot must exchange with objects nor the terrain it must stand on. Existing controllers address one side of this gap: force-capable policies command an end-effector force but prescribe no whole-body pose, while terrain-adaptive trackers treat loads as disturbances to reject rather than wrenches to command. We present BRACE, a whole-body tracker that exerts and compensate…

Knowledge distillation (KD) frameworks place teacher and student on the same GPUs, so per-GPU memory limits the teachers that fit. DisaggKD separates them across nodes: teacher replicas stream hidden states to the student, a KD loss over row windows and vocabulary shards equals the full-vocabulary loss in exact arithmetic without forming the full-vocabulary logits, and a prefetch ring paces producer and trainer. Closed-form memory and traffic models locate the memory limits of each layout. On the Qwen3.5-35B-A3B to 9B pair, the disaggregated layout matches the LM loss of the colocated run w…

Enhancing the agentic capabilities of Large Language Models (LLMs) to tackle complex software engineering (SWE) and general terminal-usage problems is a pressing challenge. Current state-of-the-art LLMs often go through large-scale agentic Reinforcement Learning (RL). However, they mostly rely on high-level outcome rewards, with minimal consideration of low-level toolcall and mid-level workflow-stage rewards, which makes the training less effective. To overcome this limitation, we propose **Lean4AgenticRL**, which, to the best of our knowledge, is the first framework that grounds multi-leve…

Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily evaluate development toward fixed specifications. We introduce EvoWeb, a novel benchmark comprising 320 cumulative requests over 32 web applications, grounded in real-world product features and structured by functional dependency graphs. Agents iteratively modify a persistent codebase, while a multimodal web agent tests each intermediate application in a live browser, assessing newly requested functionality, cross-request integration, and pre…