Google Research Open-Sources Harness², a Self-Improvement Framework for AI Agents
Google Research has open-sourced Harness², a framework that enables AI agents to iteratively improve their own prompts, tools, memory, and workflows.
#AI Agents
TAU-HOME.COM stories tagged AI Agents.
1Password Announces '1Password for Agents' Security Platform for AI Agents
1Password has announced '1Password for Agents', a security platform that securely auto-fills credentials for AI agents without exposing raw passwords. It integr
Pypestream Opens Its AI Agents to Enterprise-Built Interfaces
Pypestream's Engagement API is a REST interface that connects its enterprise AI agents to messaging platforms, mobile apps, embedded web surfaces and backend sy
Headroom Compresses Agent Context Locally Before It Reaches the LLM
Headroom is an Apache-2.0 library, proxy, and MCP server that compresses tool outputs, logs, and RAG chunks locally, with reversible caching of originals.
Cloudflare Open-Sources security-audit-skill for Multi-Agent Code Auditing
Cloudflare has open-sourced security-audit-skill under the MIT License, enabling coding agents to conduct multi-phase security audits with cross-agent verificat
GoDaddy Expands Developer APIs: Programmable Infrastructure for AI-Driven Businesses
GoDaddy expanded its Developer Platform with hosting, email, and commerce APIs, giving developers and AI agents a programmable path to launch businesses.
DeepSeek Releases V4.1-Flash-1017 with Enhanced Coding and Agent Performance
DeepSeek announced DeepSeek-V4.1-Flash-1017 on October 17, 2026, improving coding benchmarks, multi-step agent reasoning, a 1M token context, and MIT licensing.
Meta Unveils Frontier Agent Models 'Muse Wonder' and 'Muse Wonder Full'
Meta Superintelligence Labs has introduced Muse Wonder and Muse Wonder Full, next-generation frontier models built for personal and professional agentic workflo
DeepRSI Unveiled: Measuring Recursive Self-Improvement in AI Agents with 48-Hour Long-Horizon Tasks
The hillclimb research team led by Jun Park has officially released DeepRSI, an evaluation benchmark measuring recursive self-improvement (RSI) across 48-hour c
15 Open-Source Repositories for AI Agent 3D Production Pipelines
A curated collection of 15 open-source GitHub repositories bridging AI coding agents with 3D workflows: from asset generation and USD scenes to game engine cont
The Reality Behind the Claim That Open-Source MCP 'REA' Reverse Engineers Any App
Sorting out what the open-source MCP 'REA' claims to do for AI agents, where verification stops, and the safety caveats around its repository lead.
10 Open-Source Repositories and Architecture Patterns Giving AI Agents Persistent Memory
An overview of 10 open-source repositories and architectural approaches that bring persistent memory to AI agents across user preferences, temporal knowledge gr
Cutting Agent Harness Costs by Up to 3x with Lean Prompts and Tool Schemas
Optimizing the system prompt and tool schema sizes in an agent harness can reduce execution costs by up to 3x without degrading benchmark accuracy when using th
CocoIndex Code: Local AST-Based Semantic Codebase Search Cutting Agent Tokens by 70%
CocoIndex Code provides local AST chunking and semantic embeddings to search codebases by meaning without external API keys, cutting context token consumption f
Claude Workflow v2: Universal Claude Code Plugin Automating Commits and Debugging
The open-source claude-workflow-v2 plugin brings 7 specialized agents, 26 slash commands, and skills.sh compatibility to Claude Code, Cursor, and 35+ AI agent e
Academic Research Skills: An Open-Source Claude Code Agent Toolchain for the Complete Scientific Research Lifecycle
With over 48,000 GitHub stars, Academic Research Skills combines 13 deep-research agents and strict hard gates to guide literature discovery, drafting, and peer
ai-engineering-from-scratch: 523 Hands-On Lessons from Raw Math to Agent Swarms and MCP
An in-depth guide to ai-engineering-from-scratch, an MIT-licensed free open-source curriculum spanning 20 phases and 523 lessons that builds AI systems by hand
10 Practical Experiment Blueprints for the TypeSafe Jev API
A 10-project practical checklist to start experimenting with TypeSafe Jev's lightweight decision API—spanning accessibility-tree desktop automation, emulator co
Building a 24/7 Five-Agent AI Research Team with OpenAI Dots: Workflow and Safety Ladder
A practical guide to building an always-on AI research team with OpenAI Dots, distributing literature review, repro fix PRs via Codex Cloud, data analysis, sign
The 5 Core Principles of Forward Deployed Engineers: An Enterprise AI Agent Deployment Guide
A practical guide to the 5 core principles of Forward Deployed Engineers (FDEs) deploying AI agents in Fortune 500 enterprises: listening first, 4-bucket workfl
Japanese Developer Ryoma Nakajima Releases Open-Source AI Video Editor 'AKARI Video' v1.0.0
Japanese engineer Ryoma Nakajima officially released AI-native video editor AKARI Video v1.0.0 on October 2, 2026. The MIT-licensed open-source tool connects to
herdr-projects: Multi-Agent Parallel Branch Orchestration for the Herdr Ecosystem
A look at herdr-projects, a Herdr plugin letting a single coordinator run parallel agent threads across dedicated Git branches with sidebar progress tracking an
AI's 'Internet Moment': A Guide to Using Jev, a Decision Engine Up to 193x Faster and 444x Cheaper
In the era of Claude Fable 5.1 and GPT-6 Astra, Jev offers an agent architecture that separates intelligence from execution, boosting decision speed through a 1
Boosting Hermes Agent Intelligence with Planning and Source-First Verification
Discover prompt engineering tips to improve Hermes agent accuracy by enforcing pre-task planning, prerequisite validation, and source-based verification.
Pi: An Open-Source Toolkit for AI Agent Development
A comprehensive toolkit for AI agent development, offering a unified LLM API, agent loop, TUI, and coding agent CLI.
Awesome LLM Apps: A Repository of 100+ Open-Source AI Agents and RAG Apps
A repository featuring over 100 open-source AI agents, RAG applications, and agent skills ready for cloning and deployment. Supports various LLMs and released u
DeskcommCRM: An Open-Source CRM with Native WhatsApp AI Sales Agents
Explore DeskcommCRM, an open-source self-hosted sales CRM combining Next.js 16, Supabase, and WAHA with native AI agents for WhatsApp-based customer outreach an
Building Persistent Workspaces with GPT-6 Astra and Sandbox Agents
A practical guide to OpenAI's Sandbox Agents preview: build isolated agent workspaces with scoped permissions, shell execution, and session resume without rebui