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

👀38

🔥88

Sortie: Apache-2.0 orchestrator that turns GitHub/GitLab/Linear/Jira tickets into isolated coding-agent sessions via WORKFLOW.md

Dan Kornas (@DanKornas) launched Apache-2.0 open-source Sortie: define tracker, coding agent, and concurrency in WORKFLOW.md beside the repo, then schedule GitHub/GitLab/Gitea/Linear/Jira issues into isolated workspaces. Adapters cover Claude Code, Copilot, OpenCode, Codex, and Kiro, with SQLite run history, retry queues, and stall detection.

Key Takeaways

Ship: Apache-2.0 open-source sortie-ai/sortie ticket-to-agent orchestrator.
Config: single WORKFLOW.md for trackers, concurrency, and isolated workspaces.
Adapters: Claude Code / Copilot / OpenCode / Codex / Kiro with SQLite state and stall detection.

Read full story

Linked Models & Agents:

🤖 Claude Code (Anthropic)🤖 openai-codex

#Sortie#Orchestrator#WORKFLOW.md#Claude Code#Codex#Copilot#Linear#Jira#Apache-2.0#Open source

Marwan Atef@Marwan_3atef·Collected 59d ago

👀51

🔥93

View on 𝕏 ↗

AWS: Bedrock AgentCore Runtime hosts coding agents with Firecracker microVMs and persistent workspace

An AWS Machine Learning blog covers hosting coding agents on Amazon Bedrock AgentCore Runtime: each session gets a Firecracker microVM, /mnt/workspace survives idle, agentcore exec --it provides a real PTY, and Gateway MCP keeps GitHub/Jira tokens out of the VM. Run Claude Code, Codex, Kiro, and Cursor in isolation without localhost port fights.

Key Takeaways

Isolation: per-session Firecracker microVM with persistent /mnt/workspace.
Security: Gateway MCP holds GitHub/Jira tokens outside the VM.
Use case: race Claude Code / Codex / Kiro / Cursor on the same issue.

Read full story

Linked Models & Agents:

🤖 Claude Code (Anthropic)🌐 Amazon AWS (Nova)

#AWS#Bedrock#AgentCore Runtime#Firecracker#Claude Code#Codex#Kiro#Cursor#MCP

Marwan Atef@Marwan_3atef·Collected 59d ago

👀47

🔥93

View on 𝕏 ↗

AWS open-sources Agent-EvalKit: six-phase agent evals via slash commands in Claude Code / Kiro / Kilo

AWS open-sourced awslabs/Agent-EvalKit: run evals inside Claude Code, Kiro CLI, or Kilo Code via slash commands like /evalkit.plan and /evalkit.report. Six phases cover plan, data, OpenTelemetry traces, run, score, and code-linked fixes; a travel-research demo scored Response Quality 83.9%, Tool Parameter Accuracy 64.5%, Faithfulness 32.3%—pretty replies still invented temps and FX rates over empty tool results. An AWS ML blog documents the systematic eval approach.

Key Takeaways

Open source: awslabs/Agent-EvalKit with slash commands in Claude Code / Kiro / Kilo.
Pipeline: plan → data → OTel traces → run → score → code-linked fixes.
Insight: demo Faithfulness only 32.3%; empty tool results still hallucinate facts.

Read full story

Linked Models & Agents:

🤖 Claude Code (Anthropic)🌐 Amazon AWS (Nova)

#AWS#Agent-EvalKit#Claude Code#Kiro#Kilo#OpenTelemetry#agent eval#Awslabs

OpenAI Developers@OpenAIDevs·Collected 65d ago

👀60

🔥92

View on 𝕏 ↗

OpenAI and AWS put GPT-5.6 in Kiro; Terra cuts cost per successful Terminal-Bench 2.1 task by about 82%

OpenAI Developers said they worked with AWS to optimize GPT-5.6 inside Kiro. In Kiro's spec-driven environment, GPT-5.6 Terra delivered about an 82% cost reduction per successful Terminal-Bench 2.1 task. The pairing brings Sol, Terra, and Luna into AWS's requirements-to-implementation workflow with property-based testing gates, targeting long-running software work rather than one-shot completion.

Key Takeaways

GPT-5.6 Sol, Terra, and Luna now power AWS Kiro's spec-driven coding workflow.
OpenAI reports ~82% lower cost per successful Terminal-Bench 2.1 task for Terra in Kiro.
Kiro pairs specs, review checkpoints, and property-based tests for long-running agents.

Read full story

Linked Models & Agents:

⚡ GPT-5.6 Sol ⚡ GPT-5.6 Terra ⚡ GPT-5.6 Luna 🌐 OpenAI 🌐 Amazon AWS (Nova)

#OpenAI#Aws#Kiro#Gpt 5 6#Terminal bench