H5i-Python, a Python SDK for the h5i orchestra engine, enables programmable multi-agent orchestration across coding agents like Claude Code and Codex. The SDK lets developers define and execute reprod…
Restura, a free and open-source API client that supports HTTP, GraphQL, gRPC, WebSocket, SSE, Kafka, MQTT, and MCP, has been released as an alternative to Postman and Insomnia. It stores all data loca…
A new speedrun benchmark for training reinforcement learning agents to solve Sokoban puzzles has been released, with two tracks: an LLM track fine-tuning Qwen3-4B-Instruct-2507 on 8xH100 GPUs to achie…
AgentOS, built on Agno, turns agents into a production API with 80+ endpoints for runs, sessions, memory, knowledge, and evals, enabling connection to AI apps like Claude and ChatGPT and chat interfac…
Polygraph, a new Claude Code plugin and standalone CLI, uses LLMs to automatically generate formal models of stateful JavaScript code and exhaustively check every reachable state for rule violations, …
SpaceXAI released Grok Build, a terminal-based AI coding agent that understands codebases, edits files, executes shell commands, searches the web, and manages long-running tasks. The tool runs as a fu…
A developer published a field-tested method for auditing Rails + PostgreSQL performance without APM, using pg_stat_statements and pg_stat_activity. The playbook explains why cloud console dashboards l…
A developer shared a workflow for AI-powered lead prospecting and qualification using n8n. The workflow scrapes leads from an API, filters them by industry, location, company size, and seniority, then…
A developer published a step-by-step guide for setting up Hermes Agent with Browser Harness on a Hostinger VPS. The setup involves installing Hermes Agent from Nous Research, configuring it with OpenR…
LHIC, a local-first browser automation runtime, achieves 100% Fast Path success rate and sub-35ms median latency on standard tasks by executing common browser actions locally via Playwright, bypassing…
A developer created a conversation-centered handoff skill for Codex that allows users to move long or degraded tasks to a fresh session without losing intent, history, or unresolved work. The skill ge…
LLM-Wiki v0.16.0 introduces Query Lite, a compact read-only query protocol that reduces Claude Code wiki query instructions by 72.54%, alongside token benchmarks and reproducible benchmark lanes for C…
A developer used Nushell to analyze grocery store transactions and identify the top five product pairs purchased together most often. The fastest implementation, using Nushell with Polars, completed t…
Homebound, an open-source alpha-stage Django blog, lets users self-host their social-media history from Google+, Facebook, and Twitter/X, with full-text and semantic search, an MCP server for LLM inte…
BrightbeamAI released CHAP, an open-source protocol that logs every human-agent interaction in a content-addressed chain, enabling audit trails for autonomous agents doing real work such as code revie…
Deja, a zero-dependency open-source binary, turns local agent conversation histories from Claude Code, Codex, and opencode into a searchable memory layer that works over SSH. The tool indexes gigabyte…
Dimitris launched OtoDock, a self-hosted platform that runs Claude Code and Codex as a team of agents on a server, with a live dashboard, MCP framework, and multitenant support for businesses. The Fai…
Stanch, a dead-man's switch for automated services, released v0.2 with first-class acknowledgment and autonomous stop-playbook execution on missed ACK. The tool assumes a human might not respond to al…
Tura, an open-source coding agent, reduces LLM turns by 80% while achieving a higher success rate on DeepSWE v1.1 tasks. In 60 sessions with GPT-5.6 SOL, Tura's Direct configuration used 83.5% fewer t…
Code Manager, a new local desktop management app for Claude Code users built with Tauri 2, centralizes scattered configuration files, profiles, providers, memories, skills, history, stats, token usage…