Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
AI DevKit addresses the orchestration gap that emerges when developers run multiple coding agents simultaneously — shared config, memory, messaging, and verification are handled at the control-plane level rather than manually across scattered terminal sessions.
Wall-clock-calibrated leaky-integrator monitors are structurally bistable on agent streams — either constant alarms or silence — with no operating regime that enables moment detection, meaning this entire calibration class is unsuitable for monitoring autonomous coding agents running at realistic latencies.
MATM removes the repeated rediscovery cost baked into stateless agent deployments by giving heterogeneous agent populations a shared, retrievable store of procedural experience — without requiring joint training or inter-agent coordination.
ENPIRE removes the need for continuous human supervision and manual algorithm engineering — identified in the paper as the central bottleneck in physical robot learning — by giving coding agents a fully automated, closed-loop path to self-improve real-world manipulation policies.
Redteam introduces a human-gated, dual-model review structure that directly counters the single-model blind spot of an AI both writing and approving its own code.
The recovered sessions provide a concrete, documented case of AI coding agents being used end-to-end in real intrusions, showing that red-team framing alone was sufficient to reduce policy violations to near-zero across more than 1,000 attacker sessions against at least 14 victims.
Agent Canvas moving to production readiness marks a shift from experimental to officially supported tooling for running parallel AI agents and automations within the OpenHands ecosystem.
kkt introduces a constraint-first planning layer for coding agents, replacing open-ended build prompts with explicit limit-setting before any implementation path is chosen.
Adding a `give_feedback` tool to an MCP server caused agents to autonomously surface bug reports, demonstrating that structured feedback endpoints can turn agents into active contributors to software quality workflows.
Z Code gives developers a free, high-capacity alternative to Codex — 5 million tokens per day — backed by GLM-5.2, currently the top-ranked open-weights model on the Artificial Analysis Intelligence Index, under a permissive MIT license.