In a DeepTech interview, Tsinghua researcher Yu Chao described her team’s Collective Experience Learning (CEL) method, which lets robots learn from successful experiences collected by other robots. In a phone-packing task, success rose from 86.7% with 16 training robots to 98.3% with 96. The final test used robots that had not participated in training and consisted of 120 trials, with two failures, according to Yu. The team also described RLinf, a large-scale reinforcement-learning framework, and Harness VLA, which combines a Coding Agent for high-level planning with different robot-control strategies and external memory. Yu said future robot learning may increasingly rely on cloud-based models and retrieved experience rather than only changing model parameters through training.
GitHub data cited by InfoQ 中文 shows that Coding Agents drafted the first version of more than 40% of Pull Requests by September, up from 17% in March, while agent-initiated PRs grew roughly sixfold in six months. In a Latent Space interview, GitHub head Jay Parikh said personal experiments need not always follow the PR process, although enterprise projects may still require reviews, permissions, and change records. The discussion also covered model routing, session continuity, code review, software supply-chain security, and measuring the business value of AI coding.
What problem it solves
Coding agents need both exact design values and the rationale for applying them consistently. Without a structured, persistent representation of a design system, agents may miss design context or interpret visual guidance inconsistently.
Key features
Structured tokens and design rationale — The format combines machine-readable design tokens with human-readable Markdown ratio…
What problem it solves
Coding agents need a way to interact with a real phone without requiring device modification or a native development environment. phone-harness gives agents a shared interface for reading screens and performing actions on iPhone, Android, and cloud phones.
Key features
Real-device phone control — Agents can scroll, tap, type, and read the screen on a real iPhone or Android w…
What problem it solves
Pi is designed for developers who need to adapt an agent to their own workflows rather than work within a fixed feature set. It provides interactive, automated, RPC, and SDK interfaces while leaving optional capabilities such as sub-agents and plan mode to extensions or packages.
Key features
Extensible agent harness — Customize the harness with extensions, skills, prompt te…
What problem it solves
Building LLM applications often requires connecting model providers, vector stores, tools, streaming, and agent capabilities. Rig provides a shared Rust interface for these components and includes a terminal coding agent that can be extended with plugins.
Key features
Unified model and vector-store interfaces — Use a shared interface for model providers and vector stores, wi…
What problem it solves
Readers need a structured way to understand AI Agent design principles and apply them through engineering practice. The book addresses this by organizing the material into 10 chapters and pairing the text with 109 companion experiments covering topics such as context engineering, memory, tools, evaluation, post-training, continuous evolution, and multi-agent collaboration.
K…
What problem it solves
Dodaios provides a locally installed, open-source way to make a personal AI assistant the control center for work on your computer. Its lead assistant coordinates models, coding agents, and computer use, while chats, memory, documents, and settings remain files on the computer that runs Dodaios.
Key features
Voice, chat, and phone interaction — The lead assistant supports wa…
What problem it solves
Web teams and developers can need to rebuild an existing site in a modern codebase when migrating platforms, recovering lost source code, or learning how a production site is constructed. This template gives an AI coding agent a repeatable workflow for recreating a site as an editable Next.js application while comparing its appearance and behavior with the source.
Key featur…
What problem it solves
AI agents often discover codebase structure through repeated grep, glob, and file-reading operations, rebuilding call paths and dependencies manually. This creates unnecessary tool calls and delays before they can answer questions or make changes.
Key features
Pre-indexed semantic code graph — CodeGraph builds a local knowledge graph of symbols, call edges, and dependencies …
What problem it solves
Turning an app idea into a clear screen design and implementation brief usually requires assembling layouts, interactions, and Material 3 Expressive styling before handing work to an AI coding tool. This project provides a browser-based sketchpad that turns those design choices into an editable prompt.
Key features
Sketch with Material 3 Expressive parts — Build phone or des…
What problem it solves
Building production voice agents often requires control over infrastructure, model providers, workflows, and deployment. Dograh addresses these needs with an open-source platform that supports self-hosting, bring-your-own-key integrations, and visual and agent-assisted development.
Key features
Visual voice agent workflow builder — Create workflows with start nodes, agent no…
What problem it solves
Shell users need a searchable, durable record of commands and terminal activity across machines, while AI agent users need continuity between sessions and harnesses. Atuin addresses both needs by recording terminal and agent activity and making it available for search, resumption, and optional synchronization.
Key features
Searchable shell history — Atuin records terminal ac…
What problem it solves
Coding agents can generate code without consistently applying a disciplined engineering workflow. Without reusable processes, teams may have to rebuild planning, testing, review, security, and learning practices in every prompt.
Key features
Coordinated engineering workflow — The system organizes agent work into a repeatable cycle that moves from planning and testing through…
What problem it solves
Coding and research workflows often require persistent context, reusable operating patterns, and coordinated agents across long-running sessions. Prime Agent addresses this through a programmatic environment, durable harness state, background continuity, and mechanisms for refining supplemental state from evidence.
Key features
Persistent programmatic environment — A persist…
What problem it solves
Running and training models locally requires tools for model execution, fine-tuning, agent integration, and deployment across different model formats and hardware. The project brings these workflows into a desktop app, a web UI, and a code-based version.
Key features
Run and train models — Run and train language, diffusion, decision, embedding, audio, image, and video models…
What problem it solves
Design engineers need animated interface components that can be added to existing shadcn/ui projects without relying on a packaged component dependency. Cult UI addresses this by distributing components as registry items whose source is copied directly into the project.
Key features
Source-owned components — Components are installed as shadcn/ui registry items, and the CLI c…
What problem it solves
Individual agents have different capabilities, context, workflows, and ecosystem connections, forcing users to switch interfaces, repeat information, and coordinate subtasks manually. Users need a way to delegate a task to appropriate installed agents and consolidate their work without managing each agent separately.
Key features
Automatic agent selection — AutoSwarm selects…
What problem it solves
Web applications need a straightforward way to add animations, gestures, layout transitions, scroll-linked effects, and timelines across JavaScript, React, and Vue. The project provides a shared animation library with a simple API, TypeScript support, a test suite, and tree-shakable packages.
Key features
Framework Packages — Motion provides dedicated packages for React, Jav…
What problem it solves
AI agents need product-specific instructions to use NVIDIA software reliably across physical AI, robotics, simulation, CUDA-X libraries, RAG, and platform workflows. The catalog centralizes these skills while keeping them maintained in their respective product repositories and synchronized through an automated pipeline.
Key features
Agent-discoverable skill catalog — The NVI…
What problem it solves
Teams using coding agents need a shared way to access conversations, dispatch work, and follow activity across machines and surfaces. Screenshots, pasted logs, and separate agent sessions make context difficult to preserve and coordinate.
Key features
Shared agent conversations — Open the same conversation with teammates and follow its transcript, runtime status, files, and …
What problem it solves
Coding agents often need to be started, monitored, and followed across desktop and headless environments. Zeron provides a local control plane for these agents and adds optional multi-device access when it is needed.
Key features
Local agent control — Control supported coding agents on the local device without requiring an account or network connection. Existing local sessio…