Sep 1, 2026ToolsLaunchToolsPerplexity Documents Versioned Agent API Profiles for Pinning Stable ConfigurationsThe configuration layer packages a run’s model, instructions and tools under one ID. Teams can pin a known setup, while requests using latest automatically take newly uploaded versions.2 min
Sep 1, 2026ToolsToolsBoomi Details How Scribe Turns Integration XML Into AI DocumentationThe system uses one structured process representation for two different jobs: generating readable workflow records and comparing revisions for additions, modifications, and deletions.2 min
Sep 1, 2026ToolsLaunchToolsOpenClaw 2026.8.2 Adds Linux Desktop Access and Safer Agent Session RecoveryThe new release moves agent work closer to the desktop and active browser page, while adding recovery checks intended to prevent an update or migration failure from becoming a false success.3 min
Sep 1, 2026ToolsOpen releaseToolsAWS Publishes Jamf’s Bedrock Budget Gate, Restricting Premium Models at 80% SpendThe open sample makes AI cost controls more operational: developers can keep working on a cheaper model, while premium access is automatically narrowed as each person approaches a daily limit.4 min
Aug 31, 2026ToolsOpen releaseToolsTailscale Releases Tailcat for Encrypted Machine Links Without Accounts or AdminsThe new open-source utility makes Tailscale’s connection layer available to isolated and short-lived systems, but leaves token sharing, access decisions and reliable fallback infrastructure outside the tool.2 min
Aug 31, 2026ToolsOpen releaseToolsVercel Says design.md Cut Known Page Failures 57%, but All Six Pages Still BlockedThe public guidance file is meant to give agents a shared design vocabulary outside a company repository. Its early result is promising, but the small, company-run test still found a shipping-blocking problem in every generated page.3 min
Aug 31, 2026ToolsOpen releaseToolsVanta Releases 65 Agent Controls, Drawing a Line Between Governance and Runtime EnforcementThe open-source library gives organizations a shared way to document and assess agent risk, but it does not stop an agent action while it is running.2 min
Aug 31, 2026ToolsLaunchToolsGoogle Updates Antigravity Teamwork, Putting Long-Running Agent Critique in Paid PreviewThe update packages critique, verification and synthesis into reusable agent-team patterns. Google’s results suggest the orchestration can produce useful work, while the preview’s lower-parallelism setup and model mix limit direct comparisons with its research runs.3 min
Aug 31, 2026ToolsLaunchToolsMuse Code Exits Beta With Agent SDK Preview and Monthly PlansThe coding tool now offers a preview route for developers to build agents on top of it, while pricing and access mechanics remain unannounced.2 min
Aug 31, 2026ToolsOpen releaseToolsGoogle Showcases HEIR, an Encrypted-AI Compiler, With Four Private-Inference DemosThe open-source tool is meant to turn a cryptography-heavy conversion task into a development workflow. Its four CPU-based examples show possible uses; promised accelerator latency results remain ahead.2 min
Aug 28, 2026ToolsBenchmarkToolsLemmalog Turns Agent Memory Into Datalog State, Cutting LongMemEval Context 38-FoldThe experimental system moves long-running agent work away from recalling old notes and toward maintaining conclusions with explicit support. Its early benchmark results suggest a substantial context-saving path, while leaving the probabilistic extraction step as the central weakness.3 min
Aug 28, 2026ToolsBenchmarkToolsPerplexity Search API Sweeps Artificial Analysis Test, but Medium Context WinsThe result gives developers a concrete retrieval-quality lead to test, while showing that sending an agent more page text is not automatically the best route to better answers.3 min
Aug 28, 2026ToolsOpen releaseToolsNVIDIA’s TensorRT Model Connect Skips ONNX, but x86_64 Users Must Build From SourceThe open-source preview turns model conversion into a versioned deployment artifact, separating engine construction from native inference while imposing an ARM-first installation path.3 min
Aug 28, 2026ToolsOpen releaseToolsIntel Releases 20 Agent Skills for Arc GPUs, With an Open-Port Security CatchThe open repository turns Intel’s GPU deployment steps into reusable instructions for coding agents, but several model-server launchers bind broadly without authentication by default.3 min
Aug 28, 2026ToolsLaunchToolsPerplexity’s GitHub-Slack Agent Uses One API Call and a One-Reply GuardrailThe useful shift is not autonomous code changes: it is a constrained investigation loop that can authenticate to one repository, trace a fix, and report back without widening its Slack or GitHub scope.3 min
Aug 28, 2026ToolsOpen releaseToolsVisa’s VVAH Adds AI Patch Writing Across 11 Stages, Leaving Merge Decisions to HumansThe open-source harness now moves from detection through candidate remediation and adversarial validation. Its default can alter a repository’s working copy, while build, test, review, and merge controls remain outside the tool.3 min
Aug 27, 2026ToolsOpen releaseToolsExperiential Open-Sources an Agent Router That Learns From Traffic, but Results Are UnverifiedThe project turns an agent’s past requests into evidence for model selection and training, but its cost and quality gains remain company-run benchmark results.3 min
Aug 27, 2026ToolsLaunchToolsOpenAI’s 10-Day WebMCP Challenge Pushes Websites to Expose Tools for AI AgentsThe contest is an early test of whether sites will publish agent-facing actions instead of relying only on interfaces designed for human clicks.3 min