AI Coding Live News — Real-Time 𝕏/Twitter Updates & Breakthroughs

Perplexity@perplexity_ai·Collected 14d ago

👀76

🔥96

Perplexity Computer Launches Natively on macOS: Full On-Device Model and Agent Execution Without Cloud Roundtrips

Perplexity officially unveiled that Perplexity Computer now operates 100% locally on macOS through the native desktop application. Breaking away from cloud-dependent computer-use paradigms that ship continuous video feeds across the internet, Perplexity Computer executes both the underlying inference model and the agent orchestration runtime directly on local Mac silicon. By interfacing natively with macOS Accessibility APIs, the system eliminates network latency, guarantees complete screen privacy, and empowers autonomous desktop copilots to orchestrate multi-application workflows entirely offline.

Key Takeaways

Perplexity launched Perplexity Computer inside the native macOS app, hosting both model inference and agent loops locally
Eliminates privacy vulnerabilities of cloud-based GUI agents by keeping all screen frames and keystrokes strictly on-device
Achieves near-instantaneous interaction latency leveraging Apple Silicon unified memory and the Neural Engine
Seamlessly interfaces with native macOS Accessibility APIs and app sandboxes for cross-application workflow automation

Read full story

Linked Models & Agents:

🤖 Perplexity Computer 🌐 Perplexity 🌐 Apple

#Perplexity#Computer Use#macOS#On-Device AI#Desktop Agent#Privacy

GitHub@github·Collected 33d ago

👀134

🔥95

GitHub Copilot Dynamic Workflows public preview: code-defined multi-agent orchestration across CLI, app, and SDK

GitHub’s 2026-10-01 Changelog launched Dynamic Workflows in public preview for Copilot CLI, the Copilot app, and the SDK: code-defined reusable orchestration (sequential/parallel steps, pause checkpoints, subagent cross-checks)—unlike Autopilot or /fleet, where Copilot invents the plan each run. CLI needs --experimental or /experimental on; available on all Copilot plans.

Key Takeaways

Anchors: Oct 1 Changelog + docs concepts + how-to pages linked above
Code defines steps/conditions/handoffs; agents handle judgment. Distinct from Autopilot and /fleet
Surfaces: CLI workflow run + /workflows; App Workflows button; SDK/extension canvases; share via personal or repo extensions
Limits: max concurrent/total subagents, timeoutSeconds, approx maxAiCredits; prompt > workflow code > personal defaults
Public preview; CLI experimental flag; no published agent-bench deltas—don’t conflate with HydraFusion or Computer Use

Read full story

Linked Models & Agents:

🤖 github-copilot 🤖 copilot-cli 🌐 github 🌐 Microsoft Azure AI

#GitHub Copilot#Dynamic Workflows#Copilot CLI#Multi agent#Orchestration#public preview#Extensions#/fleet#Autopilot

OpenHands@OpenHandsAI·Collected 41d ago

👀81

🔥93

OpenHands v1.23.0 Released: Upgraded Multi-Agent Orchestration & Autonomous Regression Validation

OpenHands (@OpenHandsAI, formerly OpenDevin) has released v1.23.0. This release significantly upgrades the multi-agent execution pipeline and sandboxed runtime, introduces automated regression evaluation suites for complex repositories, and enhances compatibility with local inference backends like vLLM and Ollama.

Key Takeaways

Introduces tri-agent architecture (Planner, Coder, Verifier) for robust end-to-end PR resolution.
Local Docker sandbox runtime execution latency reduced by 35% with real-time file event watchers.
Built-in SWE-bench Verified regression runner for local evaluation of custom agent policies.
Full source code and container images released on GitHub with native local backend support.

Read full story

Linked Models & Agents:

⚡ DeepSeek-V3 ⚡ Qwen 2.5 Coder 32B 🤖 OpenHands (All-Hands AI)🌐 all-hands-ai

#OpenHands#OpenDevin#Coding Agents#Multi-Agent#Open Source#SWE-bench

JetBrains@jetbrains·Collected 42d ago

👀56

🔥93

View on 𝕏 ↗

JetBrains launches Air: an open agentic product system for developers, teams, and governance

JetBrains (@jetbrains) announced JetBrains Air, an open product system for agentic software development that connects IDE-side agent orchestration, team workflows, and organizational governance (formerly JetBrains Central). Air is multi-vendor: steer Claude, Codex, Gemini CLI, and JetBrains Junie inside JetBrains IDEs, and plug in other harnesses via the Agent Client Protocol (ACP). The company blog also outlines Air Teams and Air Governance.

Key Takeaways

Air unifies IDE agent UX, team workflows, and org governance as one open system.
Orchestrate multi-vendor agents (including Junie) in JetBrains IDEs; ACP for compatible harnesses.
Air Governance (ex-Central) covers policy, visibility, audit, and AI cost control.

Read full story

Linked Models & Agents:

🤖 junie 🌐 jetbrains

#JetBrains Air#ACP#Junie#agentic IDE#Governance

老

老韭菜南亥@daweifs·Collected 57d ago

👀69

🔥88

View on 𝕏 ↗

Ruflo: 70k+⭐ multi-agent orchestration that plugs into Claude Code and Codex

Ruflo is an open-source multi-agent orchestration layer (70k+ GitHub stars) for complex jobs. After npx ruflo@latest init into Claude Code or Codex, it splits work across 100+ specialized agents (code, test, security, review) with Swarm layouts, Memory, MCP, Hooks, and cross-machine collab—while you keep using the normal CLI.

Key Takeaways

Ruflo is open-source multi-agent orchestration with 70k+ GitHub stars.
Install with npx ruflo@latest init into Claude Code or Codex.
100+ agents plus Swarm, Memory, MCP, and Hooks behind the normal CLI.

Read full story

Linked Models & Agents:

🤖 Claude Code (Anthropic)🤖 openai-codex

#Ruflo#Multi agent#Claude Code#Codex#Swarm#MCP#Memory#Hooks

GitHub@github·Collected 65d ago

👀79

🔥93

GitHub Copilot Workspace rolls out multi-agent orchestration for parallel spec, code, and test execution

GitHub rolled out a multi-agent orchestration runtime for Copilot Workspace. The architecture divides software tasks across Spec, Coder, and Test agents communicating via a shared context bus. Parallelizing task formulation, implementation, and automated test synthesis cuts median feature delivery times by 55% while reducing logic regressions during complex refactors.

Key Takeaways

Linear single-agent chats evolve into parallel Spec, Coder, and Test agent swarms.
Median feature completion times drop 55% with lower regression rates in refactors.
Now generally available to GitHub Enterprise and Pro users without waitlists.

Read full story

Linked Models & Agents:

⚡ GPT-4o ⚡ Claude 3.7 Sonnet (Hybrid Reasoning)🤖 copilot 🌐 github 🌐 Microsoft Azure AI

#Github#Copilot workspace#Multi agent#Developer tools#Orchestration

Devin Desktop@devindesktop·Collected 65d ago

👀78

🔥93

View on 𝕏 ↗

Cognition Unveils Devin Desktop as Next-Generation Windsurf with Deep Autonomous Workflow Integration

Cognition announced Devin Desktop, integrating Windsurf's IDE foundation with Devin's multi-agent command center and Agent Client Protocol (ACP) for unified local and cloud agent orchestration.

Key Takeaways

Windsurf IDE evolves into Devin Desktop, providing a centralized cockpit for local and cloud agent fleets;
Native Agent Client Protocol (ACP) support enables Codex, Claude Agent, and OpenCode to share project context;
Preserves existing Windsurf keybindings, extensions, and LSP configurations; free to download at devin.ai.

Read full story

Linked Models & Agents:

⚡ OpenAI GPT-5 Codex⚡ Claude 3.7 Sonnet (Hybrid Reasoning)