All posts

agents

26 posts

NVIDIA Labs Introduces SoL-Pi for Coding Agent Efficiency
AgentsSep 11, 2026·4 min read

NVIDIA Labs Introduces SoL-Pi for Coding Agent Efficiency

NVIDIA Labs released SoL-Pi, an open-source extension for the Pi coding agent harness that reduces token usage and operational costs via recursive research.

Read more →
Cognition Releases SWE-2 Coding Model Based on Kimi K3
AgentsSep 10, 2026·4 min read

Cognition Releases SWE-2 Coding Model Based on Kimi K3

Cognition has released SWE-2, post-training Kimi K3 to match leading coding benchmarks while lowering inference costs across multiple effort levels.

Read more →
CodeRabbit Launches Agentic Security Tool for Codebase Analysis
AgentsAug 17, 2026·5 min read

CodeRabbit Launches Agentic Security Tool for Codebase Analysis

CodeRabbit has introduced a security tool that uses AI agents to identify application-specific vulnerabilities and business logic flaws across codebases.

Read more →
Perplexity Launches Python Search SDK for Agentic Workflows
AgentsAug 14, 2026·5 min read

Perplexity Launches Python Search SDK for Agentic Workflows

Perplexity has introduced a Python Search SDK centered on a 'Search as Code' philosophy, offering composable primitives for AI agent retrieval workflows.

Read more →
Microsoft Introduces Open-Source Agent for Polyglot Unit Test Generation
AgentsAug 12, 2026·5 min read

Microsoft Introduces Open-Source Agent for Polyglot Unit Test Generation

Microsoft has released an open-source testing agent that researches repositories to generate, build, and validate unit tests across multiple programming languages.

Read more →
Claude Code Introduces Cross-Session Messaging for Agent Coordination
AgentsAug 8, 2026·5 min read

Claude Code Introduces Cross-Session Messaging for Agent Coordination

Anthropic has released cross-session messaging for Claude Code, allowing independent AI sessions to communicate and coordinate tasks across terminals.

Read more →
Prime Intellect Releases Prime Agent Self-Improving RLM Framework
AgentsAug 5, 2026·4 min read

Prime Intellect Releases Prime Agent Self-Improving RLM Framework

Prime Intellect has launched Prime Agent, an open-source self-improving agent framework based on Recursive Language Models and Continual Harness architectures.

Read more →
HKUDS Releases DeepCode v2 Open-Source Coding Agent
AgentsAug 5, 2026·5 min read

HKUDS Releases DeepCode v2 Open-Source Coding Agent

HKUDS has released DeepCode v2, an open-source coding agent designed for real-world software engineering with continuous loop engineering and verified delivery.

Read more →
Cloudflare Releases @cloudflare/computer Agent Runtime Environment
AgentsAug 3, 2026·5 min read

Cloudflare Releases @cloudflare/computer Agent Runtime Environment

Cloudflare has introduced an experimental agent runtime that orchestrates between Linux containers and Workers isolates using a shared virtual filesystem.

Read more →
NVIDIA Launches NemoClaw for LangChain Deep Agents Code: Run Open-source dcode, tuned for Nemotron 3 Ultra, to Plan, Edit, and Test Code
AgentsJul 18, 2026·5 min read

NVIDIA Launches NemoClaw for LangChain Deep Agents Code: Run Open-source dcode, tuned for Nemotron 3 Ultra, to Plan, Edit, and Test Code

NVIDIA NemoClaw provides a governed blueprint for deploying LangChain’s Deep Agents Code in secure, sandboxed environments for sensitive software engineering.

Read more →