AI Agents news and analysis on Web Pulse: 49187 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Chainstack disclosed on Tuesday that an external attacker gained unauthorized access to part of its infrastructure through a third-party component, reaching a development environment on October 26, 2026 and escalating in…
A developer outlined a pattern for wiring a paid captcha-solving tool into a browser-driving AI agent over MCP, covering configuration, spend limits and failure handling. The approach keeps the solver API key in the serv…
Sandchest launched a GitHub app that uses abliterated, unrestricted AI models to scan repositories for vulnerabilities and deliver findings with a step-by-step attack path, a runnable proof of concept, fix requirements, …
Hystax open-sourced OptScale Kompressor, a Rust binary that strips machine-generated noise from coding agents' context before it reaches the LLM API, cutting the provider bill by 22.7% in the company's Terminal-Bench 2.1…
Redis released the next chapter of Redis Iris, a real-time context engine for AI agents that now offers six capabilities: Intent Router, Agent Playbooks, Agent Memory and Context Gateway are generally available, while Le…
Agno shipped 13 releases in October 2026, including CompanyOS, which lets agents take ownership of off-roadmap work by reading defined Sources and proposing Projects and Tasks for team approval, and new CodexAgent and Cl…
A 300-page survey of code intelligence, "From Code Foundation Models to Agents and Applications" (Yang et al., submitted November 2025), reports that general models "do not robustly exploit very long inputs" and that rep…
A new evaluation called RoboColosseum ran 5,699 blinded pairwise comparisons at 124 sites and found that frontier AI agents rival specialized robot policies, that policy rankings shift substantially across robot bodies a…
A hands-on test of Crouton Alpha, a free, unreleased stealth model with a 1 million token context window whose maker has not been publicly confirmed, found it handled subagent-driven coding, vision and scientific reasoni…
DeepSeek released DeepSeek Harness (DSH), an open-source, MIT-licensed coding agent framework, on August 13 alongside DeepSeek V4 Pro, built on the Cordis composability framework in which every component — including the …
DeepSeek published seven official Creator Mode prompts in English and Chinese on a single page with copy buttons, showing how its open source DeepSeek Harness agent app (MIT licensed, over 269,000 GitHub stars, at releas…
Two open-source, MIT-licensed plugins built by an AI coding agent (Claude Code) add stereoscopic 3D to the Nintendo 3DS versions of Minecraft and Terraria, according to a practical installation guide. The Minecraft plugi…
An MIT paper reports that a frontier model the researchers call GPT-6 Astra directly edited a small Qwen reasoning model's weights without gradient-based training, raising the Qwen model's math benchmark score sixfold. T…
Cloudflare launched Zero Wire on November 3, 2026, a free public feed of critical-vulnerability briefings hosted in Cloudflare Radar's security section, with each card carrying a status and last-checked date and grouping…
GitHits released a `list` tool that lets coding agents browse a repository's source tree, documentation and tests, as demonstrated on the Pi coding agent at commit 9c9ce854. The tool takes a target identifier such as `gi…
The open-source news aggregator Horizon, built by GitHub user Thysrael, appeared on GitHub's weekly trending page for week 45 of 2026 and now has roughly 12.3k stars, 1.8k forks and 301 commits under the MIT license. Hor…
MoneyPrinterTurbo, an MIT-licensed AI short-video generator from developer harry0703, has reached roughly 138,500 GitHub stars and about 22,100 forks, gaining 615 stars in a day and landing on GitHub's weekly trending li…
Together AI introduced Together Compiler (TKCC), a continual agentic system that optimizes AI inference workloads, reaching 1.3-3x higher TPS across frontier open-source models including Kimi K3, GLM 5.3, MiniMax M3.1-Fl…
SemiAnalysis reported that tuning GLM-5.2-MXFP4 serving on AMD Instinct MI355X GPUs with its InferenceX AgentX benchmark raised peak per-GPU throughput 1.72×, from 10,625 total tokens/s/GPU at concurrency 10 in the Augus…
Cloudflare on November 4, 2026 added a Personal Assistants traffic category to Security Analytics and per-agent access policies, letting site owners see which personal AI agents visit and set Allow, Block on pages with a…