A specification for agent behavior that LLM frameworks leave undefined: error handling, context management, tool execution, and state transitions.
truefoundry/trueforge
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
AI Agents: Key Concepts and How They Overcome LLM Limitations
An AI agent is an autonomous software entity that is often used to augment a large language model. Here's what developers need to know.
Agents Done Right: A Framework Vision for 2026
Agents choke on context, loop on failures, and dump walls of code for review. It's time to rethink the architecture.
Build agents, not pipelines
There are only two ways to use LLMs in a computer program: as part of a pipeline, or as an agent. In other words, either you express the control flow of the program in code, or you give a LLM tools and allow it to manage the control flow itself1.
If an AI agent can’t figure out how your API works, neither can your users
Discover how LLM‑powered agents act as tireless API testers—exposing friction in docs, errors, and design—and learn six essential strategies (consistency, comprehensive docs, rich errors, example‑driven tutorials, simplicity, and feedback loops) to elevate your API’s developer experience for both humans and machines alike.
LukeW | Agent Management Interface Patterns
As an increasing number of AI applications evolve to agents doing work for people, agent management becomes a critical part of these product's design. How can p...
Model Leaderboard | Letta
Context-Bench measures an agent's ability to perform context engineering with:
Agent READMEs: An Empirical Study of Context Files for Agentic Coding
Agentic coding tools receive goals written in natural language, break them down into specific tasks, and write or execute code with minimal human intervention. Central to this process are agent context files (e.g., AGENTS.md and CLAUDE.md) that provide persistent, project-level instructions. In this paper, we conduct the first large-scale empirical study of 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content. We find that these files are not static documentation but complex, difficultto-read artifacts that evolve like configuration code through frequent, small additions. Our content analysis of 16 instruction types shows that developers prioritize functional context, such as test procedures (75.9%), implementation details (70.8%), and architecture (68.1%). We also identify a significant gap: non-functional requirements such as security (14.8%) and performance (14.5%) are rarely specified. These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tools and practices.
perplexityai/SPACE
Sandboxed Platform for Agentic Code Execution: pluggable-runtime sandboxes for running agent and user code in isolation.
perplexityai/SPACE
Sandboxed Platform for Agentic Code Execution: pluggable-runtime sandboxes for running agent and user code in isolation.
Securing the Model Context Protocol: Building a safer agentic future on Windows
As AI agents become more capable and integrated into daily workflows, the need for secure, standardized communication between tools and agents has never been greater. At Microsoft Build 2025, we’re announcing an early preview of how Windows 11 is e
Optimizing Agentic Workflows using Meta-tools
Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations,...
Harness engineering: leveraging Codex in an agent-first world
By Ryan Lopopolo, Member of the Technical Staff
Harness engineering: leveraging Codex in an agent-first world
By Ryan Lopopolo, Member of the Technical Staff