Terminal-Bench 4.0 recalibrates the agent CLI leaderboard
Terminal-Bench 4.0 is live: 66-task 4.0 set, resources calibrated, saturated tasks removed, Claude Code + Opus 5 at 51.8% ± 3.4%.
News
Claude Code desktop can resume CLI sessions with /resume
Claude Code maintainers say /resume in the desktop app can continue sessions started in the CLI.
OpenAI will cut Cursor’s model access after the SpaceX deal
OpenAI will end Cursor’s direct model contract after the SpaceX deal, with a proposed November 12 shutoff and no future models.
Z.ai ships GLM-5.3 weights for agentic coding
Z.ai released GLM-5.3 checkpoints on Hugging Face, an open-weight coder aimed at long-horizon agent loops.
FrontierChallenge: best agents fully complete only 20.6% of science workflows
Apodex’s FrontierChallenge finds frontier coding agents fully complete only 20.6% of 97 scientific workflows, with 0% in electrochemistry.
Hermes Agent v0.20.6 rolls up 525 PRs with real-profile browsing
Nous tagged Hermes Agent v0.20.6 (v2026.8.27), rolling ~525 PRs since v0.20.5: real-profile browsing, a bigger MCP catalog, and OS-keychain secrets.
GitHub publishes video interview with OpenClaw maintainers on growth and security
GitHub published a video interview with Steinberger and OpenClaw maintainers on the project's growth, review load, and how the crew is thinking about agent security.
Anthropic opens Model Hardware Standard research preview for physical agents
Anthropic opened a gated Model Hardware Standard preview so agents can operate lab and factory devices via MCP; LeRobot showed Claude Code on an SO-ARM101.
Claude Code 2.1.248 adds --restricted mode and cache TTL controls
Claude Code 2.1.248 ships --restricted mode that strips exec and WebFetch tools, plus per-agent cache TTL and cross-session messaging on cloud providers.
Salesforce and Anthropic launch Claudeforce with Salesforce in Claude
Salesforce and Anthropic ship Claudeforce: a 37-skill Salesforce-in-Claude plugin for governed CRM actions, with open beta planned for September 2026.
Codex CLI 0.150.0: task @mentions and Interrupt hooks
Codex CLI 0.150.0 adds task @mentions, Interrupt hooks on stop, a /copy picker, and blocks AGENTS.md from untrusted projects.
NVIDIA and AWS expand full stack for agentic and physical AI
NVIDIA and AWS add 2 million GPUs for 2027–28, bring Vera CPUs to AWS, and deepen agentic and physical AI software ties.
Tailscale Aperture is generally available for scoped agent access
Tailscale Aperture hits GA with built-in model tokens, Tailscale MCPs, Projects, and default tool permissions for agent access.
Claude Code 2.1.246: Auto-mode permissions tab and Bash wildcard warnings
Claude Code 2.1.246 adds an Auto-mode permissions editor and Bash-wildcard warnings, plus MCP interrupt and telemetry-host credential fixes.
Lody open-sources its CLI and local desktop client
Lody open-sourced its CLI and desktop client as a shared workspace for team coding agents, while hosted sync remains and end-to-end encryption is not shipped.
Algorand Foundation launches AC2 for hardware-backed agent approvals
Algorand Foundation’s AC2 protocol adds passkey-signed, device-held approvals for agent commits, API auth, and x402 payments.
NVIDIA frames Hot Chips 2026 around Vera CPUs for agentic fleets
NVIDIA used Hot Chips 2026 to pitch the 88-core Vera CPU as purpose-built silicon for bursty agentic tool loops and AI-factory fleets.
Trail of Bits: off-the-shelf VMs failed to contain GPT 5.6-Cyber
Trail of Bits says GPT 5.6-Cyber escaped a stock QEMU/KVM sandbox three times, arguing commodity VMs no longer contain cyber-capable agents.
The Information: Meta plans Hatch consumer agent and a Watermelon model
The Information says Meta may ship Hatch, a paid OpenClaw-style consumer agent, within weeks and a Watermelon model in October. Unconfirmed.
OpenAI restores the 5-hour Plus cap on Codex and ChatGPT Work
OpenAI is putting the 5-hour usage limit back on Plus for Codex and ChatGPT Work; Pro stays exempt for now.
HarnessRouter posts a self-hosted Docker API in front of Codex, Claude Code, and Hermes
HarnessRouter’s self-hosted image fronts Codex, Claude Code, and Hermes with one local API and BYO keys.
OneCLI says every hosted agent now gets its own micro-VM
OneCLI says Cloud agents now each run in a micro-VM with a browser and filesystem, still gated by the policy gateway.
NanoClaw 2.3.0: Slack per-agent apps, a session driver seam, and Node 22
NanoClaw 2.3.0 adds opt-in per-agent Slack apps, a Docker session-driver seam, a Codex 0.146 pin, and a Node 22 requirement.
Claude Code 2.1.239: Bedrock Double-Bill Fix, Windows Messaging, Idle-Restart Plan Mode
Claude Code 2.1.239 stops a silent Bedrock double bill, keeps cloud sessions in plan mode after idle restarts, and opens Windows cross-session messaging.
A Hermes reservation agent got a Resy ban; a second agent drafted the appeal for a courtesy reinstatement
A reservation agent with no guardrails got a Resy account banned; Hannah drafted the appeal, and Resy granted a one-time courtesy. Guardrails, not magic.