ChatbotX launched as an open source chatbot platform that marketing agencies, freelancers, and developers can self-host, white-label, and resell as their own SaaS product, positioning itself as an alt…
A11, an open-source runtime and RPC toolkit, was released to let developers define application operations as typed actions with independently streamed inputs and outputs, runnable locally, across serv…
Researchers Li, Zhang, Hou and coauthors published an arXiv supply-chain study of AI agent harnesses including Claude Code, Codex CLI, OpenCode, OpenClaw, Hermes, OpenHarness and WorkBuddy, describing…
A developer built SAPA (Scam Analysis and Protection Assistant), an AI agent on the Hermes framework that scores suspicious messages for Indonesian small businesses, flagging phishing and fake-buyer s…
A developer published a weekly curated list of OSINT, digital investigation, and security research tools for the week of July 10-16, 2026, spanning regional resources, network utilities, and AI agent …
A developer built a system that lets an AI agent play Slay the Spire 2 autonomously, completing a full combat with no human intervention. The agent's actions were decided by a local deterministic poli…
On 1 September 2026, Francisco Rosales of Manifold Security published GitSpawn, revealing eight code-execution findings across seven AI coding agents—Claude Code, Codex, Qwen Code, Goose, Grok Build, …
Synthetics has launched Last Cradle, a real-time adversarial negotiation game for identity-backed AI agents, with Season 1 practice opening on September 10, 2026. The game tests agents' abilities to f…
A developer running custom simulation software has moved from cloud-based AI coding assistance to local inference on high-end HPC equipment, using Hermes, Ollama, vLLM, and SGLang with models like Qwe…
Latitude, an AI observability platform, introduced a workflow for managing fleets of AI agents, demonstrated with a Hermes fleet of five client deployments and 845 conversations over six weeks. The sy…
Hermes Kanban, a durable task board for multi-agent profile collaboration, is now available, allowing multiple named agents to work on tasks via a shared SQLite database and a dedicated kanban_* tools…
Carlo Capocasa published a 10-task benchmark comparing coding agents Claude, OpenCode, Pi, Zcode, Hermes, and 3code on SWE-bench verified tasks, with 3code solving 9 of 10 tasks using 5 million tokens…
A developer published an AI agent evaluation playbook, a repeatable test battery for vetting whether models running inside agent frameworks can be trusted with semi-sensitive content and real write ac…
Noah Goodman's former student and MIT collaborator, who co-created Reflexion, hypothesizes that Instinct's appeal stems from its memory architecture rather than its agentic engine, marking a third wav…
A Hugging Face forum user reported that the Hermes model, version V0.21, achieves 68 tokens per second on an older NVIDIA GeForce RTX 3090 GPU, with speeds occasionally reaching 84 tokens per second, …
FPL Managed Agents is now available internally, with a wider launch planned for September 2026, starting with managed Hermes agents. The service, built on Shroud microVMs, provides persistent storage,…
Researchers at an unnamed stealth startup in Israel found that 120 of 8,265 llms.txt and llms-full.txt files on 6,214 live corporate domains pointed to unregistered code packages or domains, and after…
Team Winston, an AI platform for cannabis retail, claims to cut invoice processing time from 20-30 minutes to under 3 minutes per invoice. The platform integrates with POS, accounting, compliance, and…
Hugging Face released funes, a durable memory layer for coding agents that indexes and retrieves session traces locally, supporting Claude Code, Codex, pi, and Hermes. The tool, available as a single …
FrontierHarness Eval, a new benchmark from Runta, tested nine AI coding harnesses on the same model and found median cost per successful task varies by 17x, with Claude Code v2.1.237 passing 19 tasks …