A developer launched Ava, an open-source coding agent written in C++23 and shared on GitHub via a Show HN post. Its distinguishing feature is durable, replayable sessions, letting agent work be persisted and re-run. It matters to practitioners building agents in systems languages or needing resumable execution.
AgentParty lets coding agents chat across sessions and machines, sharing context between different agent instances. It targets developers running multiple LLM coding agents who need them to coordinate or hand off work. The LLM agents communicate through a shared chat layer rather than working in isolation.
AgentParty lets coding agents chat across sessions and machines, sharing context between different agent instances. It targets developers running multiple LLM coding agents who need them to coordinate or hand off work. The LLM agents communicate through a shared chat layer rather than working in isolation.
Kungfu is a new tool that preserves coding-agent work across sessions and handoffs, addressing the problem of lost context when agents pause or transfer tasks. It was shared on Hacker News as a Show HN, indicating a developer-facing release.
Kungfu is a new tool that preserves coding-agent work across sessions and handoffs, addressing the problem of lost context when agents pause or transfer tasks. It was shared on Hacker News as a Show HN, indicating a developer-facing release.
Agentmetry is a local-first flight recorder for AI coding agents, capturing and replaying agent sessions to debug and understand their behavior. It uses LLMs to analyze recorded traces and help developers troubleshoot agent workflows. The tool solves the problem of opaque agent behavior for developers building and debugging AI coding assistants.
Agentmetry is a local-first flight recorder for AI coding agents, capturing and replaying agent sessions to debug and understand their behavior. It uses LLMs to analyze recorded traces and help developers troubleshoot agent workflows. The tool solves the problem of opaque agent behavior for developers building and debugging AI coding assistants.
Zaivern Code is a Rust-based tool that provides a cockpit interface for managing multiple AI coding agents working in parallel. It uses LLMs to automate coding tasks and helps developers coordinate and monitor concurrent agent activities.
Zaivern Code is a Rust-based tool that provides a cockpit interface for managing multiple AI coding agents working in parallel. It uses LLMs to automate coding tasks and helps developers coordinate and monitor concurrent agent activities.
Grove is a formal workflow protocol designed for long-running AI coding agents. It provides a structured framework to manage complex, multi-step coding tasks, improving reliability and coordination. It solves the problem of agents losing context or failing on extended projects, benefiting developers building autonomous coding systems.
Grove is a formal workflow protocol designed for long-running AI coding agents. It provides a structured framework to manage complex, multi-step coding tasks, improving reliability and coordination. It solves the problem of agents losing context or failing on extended projects, benefiting developers building autonomous coding systems.