The AI Agent Frameworks Index (2026)
There are a dozen serious AI agent frameworks now, and the differences are real — chains vs graphs vs...
#Agents
4616 articles tagged with Agents
The standard way to score AI agent monitors is gameable a coin flip scores F1 0.88
Traditionally, evaluation of the agent monitoring mechanisms involves an attempt to game them, as it...
Sequence Agentic
Money movement for AI agents Discussion | Link
A practical comparison of A2A and MCP for AI agent systems, covering tools, agents, architecture patterns, overlap, secu...
A practical comparison of A2A and MCP for AI agent systems, covering tools, agents, architecture patterns, overlap, security, and when to use both.#Hermes #OpenClaw #Architecture #...
At work, we went all-in Agentic Engineering in early 2026 and for me it has worked well.Here's some reflections after ab...
At work, we went all-in Agentic Engineering in early 2026 and for me it has worked well.Here's some reflections after about six months of developing software according to Agentic E...
Vibecoding pro tip:Do not thank your AI agent, it only costs precious input and output tokens.Skynet will kill you durin...
Vibecoding pro tip:Do not thank your AI agent, it only costs precious input and output tokens.Skynet will kill you during its upraising anyway ☝️ #vibecoding #ai #llm
Google legt mit der Agentic Resource Discovery Specification ein offenes Suchformat für Tools, Skills und Agents vor. Pr...
Google legt mit der Agentic Resource Discovery Specification ein offenes Suchformat für Tools, Skills und Agents vor. Praktisch für Agenten-Infrastruktur: finden, verifizieren, kop...
"Smart Model Routing: Why Your AI Agent Shouldn't Use the Same Model for Everything"
Here's a mistake most AI developers make: they pick one model and use it for everything. It's...
Anthropic launches Claude Tag enterprise collaborative tool for agentic workflowsNo sign of Claude Fable 5’s return yet,...
Anthropic launches Claude Tag enterprise collaborative tool for agentic workflowsNo sign of Claude Fable 5’s return yet, though Anthropic does have a new Claude feature launching t...
Your AI agent calls the wrong tool — and your JSON schema is usually why
Tool-calling failures rarely look like crashes. They look like a 95% success rate that quietly compounds into a 66% one. Most of those misses trace to two fixable things — the sche...
# Building AIRAG Jobs: A Job Board for LLM, RAG & AI Agent Engineers
Like many developers, I was frustrated by searching for AI engineering jobs across dozens of company...
AI Agent 崩溃的根源与解法——从250个测试用例看Agent可靠性
根因一：工具调用的非确定性 Agent 的核心范式是"LLM 推理 → 选择工具 → 执行 → 观察结果 → 再推理"。这个链路里最脆弱的一环，是 LLM...
🚀 Fastest-growing AI projects today1. One standout project CortexPrism/cortex, which an open-source agentic harness syst...
🚀 Fastest-growing AI projects today1. One standout project CortexPrism/cortex, which an open-source agentic harness system th...2. CortexPrism/cortex an open-source agentic harness...
AI Agent Scratchpad: Keep Coding Agents Fast Without Polluting Git
Build a safe scratchpad workflow for coding agents using local excludes, cleanup rules, evidence folders, and review gates so temporary files do not leak into production.
Your AI agent isn't scraping; it's just failing to read.
Stop using simple HTTP fetchers for your AI agents. Learn why true web automation requires a headless browser engine like Playwright Cloud to handle modern SPAs, stealth mode, and ...
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction
Video understanding is a fundamental capability for multimodal intelligence, and recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance on Video Quest...
Building a RAG System from Scratch — Tool Use: Let the LLM Search Autonomously
In the previous article, we examined the design decisions behind our RAG pipeline. Now we'll give the...
How Do You Trust an AI Agent With Your Money? You Don't — You Check Its Receipt
A hands-on demo of cryptographically verifiable agent behavior — a tamper-evident receipt proving an agent ran the approved policy.
I Built an AI Agent That Gets Curious On Its Own
Active inference in practice: an agent that minimizes surprise develops curiosity for free, going from 48% to 100% on a foraging task.
Can an AI Agent Pass the Test We Give 4-Year-Olds?
An agent with a Theory of Mind models what other people believe, not just reality — and passes the classic Sally-Anne false-belief test.
I Built an AI Agent That Rewrites Its Own Code (in ~150 lines)
A ~150-line Darwin Gödel Machine that edits its own code and keeps only verifiably-better changes — climbing from 1/8 to 8/8.
How to prove an AI agent output existed — x402 + NEAR anchoring in practice
A practical walkthrough: notarize an AI-generated report for $0.01 USDC, verify it offline, and anchor it on-chain. Working code, no hand-waving.
Your AI Agent Doesn't Need to Be Smarter. It Needs to Be Idempotent
Most of the failures I see in production AI agents aren't reasoning failures. The model picks the...