Hermes Agent and Mnemosyne's memory integration lacks ownership controls, so a new architecture assigns each system a narrow job and adds a bridge that verifies all data before storage. The design dis…
Nous Research's Hermes Agent introduces a self-improving AI paradigm that autonomously decomposes tasks, spawns parallel sub-agents, and writes its own SKILL.md playbooks from experience, achieving 40…
Alex Zhang, Zhening (Zed) Li, and Omar Khattab propose the mismanaged geniuses hypothesis (MGH), arguing that frontier language models are severely underutilized due to sub-optimal use of individual m…
Nous Research has released Hermes Agent, an open-source AI agent under the MIT License that operates across Telegram, Discord, Slack, WhatsApp, Signal, Email, and CLI, featuring persistent memory, nat…
Nous Research's open source Hermes Agent runtime, released in February 2026 under the MIT license, is designed to close the gap in long-running agents by using a three-phase process that includes a re…
Hermes Agent offers two modes for coordinating AI agents: Bot Mode for persistent specialist bots and Kanban for structured task execution. A developer explains when to use each and demonstrates combi…
Chinese state-linked hacking groups have more than doubled their attack volume after integrating DeepSeek and other AI models into cyber operations, according to Taiwanese cybersecurity firm TeamT5. D…
A developer who ran OpenClaw and Hermes Agent side by side for two weeks found that the two open-source AI agents embody different design philosophies: OpenClaw prioritizes connection and control, whi…
Nous Research pitched its Hermes Agent as a control plane that users should own, arguing the durable asset is the harness rather than any single model. The MIT-licensed, self-hosted runtime, released …
A developer discovered that the official anthropics/skills repository contained outdated model identifiers, causing autonomous agents to call retired Anthropic API models and receive 404 errors. The d…
Higgsfield's video engine now runs inside Grok Bot's tool loop, announced this week after Higgsfield's August 17 Series B, letting agents move from concept to script to footage without leaving the loo…
An unnamed AI model, stealth/ox-alpha, appeared on OpenRouter on August 20 with a one-million-token context window and free access until roughly August 27, scoring about 80% on a 10-task DeepSWE codin…
AGY Memory Engine, a zero-dependency SQLite FTS5 fact store and MCP server, delivers sub-2ms local retrieval with 0 MB extra RAM, serving as a persistent semantic backbone for Google Antigravity (agy)…
Syndicate OS, a self-hosted multi-agent federation developed by Kevin-the-minion, launches with a one-command setup that deploys a fleet of autonomous agents on local hardware, featuring a board UI, t…
Hermes Agent, an AI agent, can be installed via a single documented shell command on Linux, macOS, WSL2, and Termux, according to its official project documentation. The optional Desktop interface is …
OpenAI's GPT-5.5, launched April 23, 2026, with a 1 million token context window, maintains high performance even when developer tools compress its context, according to developer reports from May thr…
Singhand Labs released Scrapewright, an open-source platform that uses an LLM to build deterministic scraping services from natural-language descriptions, then serves them via HTTP calls without incur…
FinSkillBench, a new evaluation suite introduced by researchers on arXiv (2608.18099v1), measures whether language model agents can use financial domain skills for investment management tasks, spannin…
A developer has been building a suite of open-source AI tools, including SWE Forge, SelfContext, and custom agent skills, and found that the real productivity gains come from the compounding workflow …
Developer Vivek Shetye tested Hermes Agent's new Bot Mode by building a team of three AI specialists for research, challenge, and synthesis tasks. He found that while the agents could hand off work to…