AI Briefing#ai-agents
The latest AI and developer news about #ai-agents, with the original source and a short summary.
The latest AI and developer news about #ai-agents, with the original source and a short summary.
Apiiro research identifies 2,539 real secrets in 1,994 public GitHub repositories exposed by Claude Code's local settings file, with 1,122 files containing active credentials.
The roughly 50-person AI Frontiers team, which developed the Autogen and Fara agent frameworks, is declared finished after its leader left Microsoft.
The tool uses a custom VMM and WebAssembly components to enforce strict network and filesystem policies, supporting Linux, macOS, and Windows.
The update introduces a built-in HTTPS tunnel using Let's Encrypt, Google Trust Services, and ZeroSSL that requires no account or payment.
The feature uses Plaid to access balances and transactions on Pro, Max, and Ultra plans, allowing users to query spending without giving Claude control over funds.
The tool uses 320 CLI and MCP tools to analyze native apps, websites, and games, then directs coding agents to rebuild them in a clean-room or deep mode.
The open-source Go project manages scoped, revocable access for AI agents without exposing user credentials, supporting MCP server integration.
CopilotKit has released OpenDots in alpha, providing isolated computers per agent and an editable document repository.
The study defines agent memory as persistent, experience-based knowledge and introduces 'dreaming' to correct errors, with benchmarks showing significant performance gains for newer Claude models.
Developed with Ligo, the 100-task benchmark tests AI agents on interpreting raw experimental data, where GPT-6 Astra significantly outperforms previous models.
The feature automates database setup and runs deterministic and agentic security checks before deployment.
In a 100-megawatt data center comparison, Vera achieves 2x faster agent speed than the most energy-efficient x86 CPU while maintaining leading energy efficiency.
The Indian fitness company extended Codex beyond engineering to let non-technical teams build 20+ internal apps and automate support workflows.
Rivet offers a lightweight, S3-based orchestration layer that achieves 4.99 ms p99 cold starts and 72 KB memory per actor, positioning itself as a scalable alternative to heavy sandboxes and Cloudflare Durable Objects.
The coalition aims to establish open standards for identity and accountability, while new Cloudflare tools allow site owners to identify, restrict, and trace specific AI agents.
The firm argues that existing human-centric structures fail to capture AI value, advocating for AI-native designs where agents and humans co-evolve to drive nonlinear productivity gains.
The November 2025 Model Context Protocol specification deprecates batch requests and introduces elicitation for server-to-user interaction.
Developers built a closed loop that controls agent progress without writing code directly.
The Queries API is free for all Stripe users through January 31, 2027, after which it will charge per credit of API usage.
The November 2026 report identifies four key themes: harness engineering, open-weight model adoption, multi-agent workflows, and AI factory infrastructure.
Wu cites OpenAI's reach of over a billion users and plans to build agents that keep users in control.
The update makes Devin Review the default for PRs, with a median latency of 94 seconds and new features for incremental reviews and custom checks.
The 16 million-line library is the largest integrated formalized mathematics collection, enabling direct import of algebraic geometry definitions and theorems.
The update enables developers to build and deploy agents, workflows, and apps across cloud, VPC, or on-premises environments using the Mistral Large 4 model.