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.
In a two-day test run on November 5 and 6, 2026, coding agents using ArchDocs' task-context records caught a dependency that agents relying only on repository rules files missed in 3 of 3 runs versus 0 of 3, refusing to …
Vercel's AI Gateway added Ampersand (humansand/ampersand-v0.1), a language model from Humans& built for group conversations that decides each turn whether to speak or stay quiet, and is free on the gateway through Novemb…
Billion Context, an open-source proxy that compresses conversation history between a coding agent and the model API, has reportedly passed 3,700 GitHub stars and 300 forks in about three months by exposing compress, deco…
Billion Context, an open-source proxy that compresses AI coding-agent conversation history, cut costs 58% on a coding-agent benchmark running DeepSeek V3.1 Flash ($4.61 versus $11.05 for full context) while scoring an F1…
A $2,000 AMD Radeon R9700 paired with 256GB of system RAM sustained 16 concurrent coding agents on a 124 billion parameter mixture-of-experts model, while a dual RTX Pro 6000 machine with 192GB of VRAM but only 128GB of …
A custom Blood on the Clocktower social-deduction benchmark, run by one creator who spent roughly $20,000 in API credits across 368 games, ranks GPT-6 Astra first, beating Claude Opus 4.6 in about 92% of matches — a gap …
OpenAI's GPT-6 Astra, released in September, is the strongest model tested on a Blood on the Clock Tower social-deception benchmark, beating Claude Opus 4.6 in roughly 92% of head-to-head games and leading by about 430 E…
Beo AI released NorKa, an open-weight computer-use model family in three sizes — Pro, Mini and Nano — with the Pro variant scoring 88 on OSWorld Verified. NorKa Pro is a mixture-of-experts model with 397 billion total pa…
Hands-on testing on a Threadripper Pro 9975WX workstation found that system RAM, not GPU VRAM, caps how many parallel AI coding agents a machine can sustain: with dual RTX Pro 6000 cards (192GB VRAM) and 128GB of RAM, th…
A November 6, 2026 blog post attributes most cases of Copilot ignoring copilot-instructions.md to the file never reaching the model, citing GitHub's repository instructions documentation, GitHub's custom-instructions sup…
Prod-code v0.3.52 (commit 91ec5def, published 2026-11-05) adds readOnlyHint to 11 more MCP tools, including code_impact, code_diagnostics and code_validate_edit, so MCP hosts with an approval policy of never can call the…
Explainroo, an open-source tool by developer vincentsch, lets a coding agent turn a plain-text prompt into a fully narrated, animated explainer video MP4 rendered entirely on the user's own machine. The pipeline uses the…
BasedHardware's Omi, an MIT-licensed open-source AI wearable platform, ships its firmware, hardware designs, Flutter mobile apps, macOS Swift/Python and Windows Node desktop apps, and backend in a single public GitHub re…
GitHits released githits-scan 0.3.0, a command-line tool that finds the lockfiles and manifests in a repository and uses GitHits to generate a software bill of materials, audit dependencies, and report or check licenses.…
AMD released PrimusClaw, an open-source managed agent runtime for Kubernetes clusters running AMD Instinct GPUs, which has been in production at AMD since April 2026. Two PrimusClaw deployments hosted more than 40,000 ag…
Apache Airflow 3.4.0 shipped with Task Loops (AIP-111), a native bounded-iteration primitive that repeats a decorated task group up to a required max_iterations cap with an optional until predicate, plus the ability to a…
Greenlight Financial reported in a November 6, 2026 AWS Machine Learning Blog post that its Luna autonomous security operations center, built on Amazon Bedrock AgentCore, resolves 83% of security alerts without human int…
A benchmark published November 6, 2026 by Agent37 comparing its cloud sandboxes with Daytona found that 96 coding jobs on each provider's default sandbox type cost an estimated $0.051 on Agent37 versus $1.54 on Daytona, …
Stanford researchers led by Jure Leskovec proposed Memorilla, a latent semantic memory method described in arXiv:2610.21375 that feeds a frozen Qwen3-8B decoder 16 learned memory tokens instead of raw document text, usin…
Thinking Machines Lab said on 5 Nov 2026 that its Inkling 2 Small mixture-of-experts model, with 594B total parameters and 17B active, is available on Tinker with closed weights, and that the lab intends to release the f…