See what your AI coding agent actually did — and whether to trust it. A local-first, cross-agent replay + trust report you attach to a PR. Review the process, not just the diff.
Tree-inspired pi extension for reviewing session and git diffs.
Event transport, replay, and durable transcripts for AI agent conversations
Agent Experience Index Score — synthetic testing for AI agent interaction
Agent Evaluation and Observability Framework
AI control CLI for Airflow and platform operations
MCP server for Agent Wallets on Sui — 9 tools (balance, send, swap, pay, …) + 8 auto-registered skill prompts, stdio transport. Drop-in for Claude Desktop, Cursor, Windsurf, Cline, Continue, or any MCP-compatible client.
Subscription LLM auth providers for agent-qa.
AgenShield CLI binary for darwin arm64
The world's strongest free coding agent
Agent Connect command line — bridges Telegram Forum topics to Claude Code / Codex sessions in tmux
Bidirectional bridge between Claude Code and other AI coding agents (Codex, OpenClaw, Hermes, ...) over the MCP Channels protocol.
Captures Claude Code failures and recovers from them using the Skipshot trajectory marketplace.
No description provided.
Onklave Agent CLI — local agent runner with cloud orchestration
The command line interface for Justd.
Reports diff images for failing image snapshot tests
Command-line tools for local Univer workbook automation.
A grab-bag of small, tree-shakeable helpers shared across the Lindorm packages: deep object diff/merge, predicate-based array querying, abort-signal composition, and other day-to-day utilities.
Harness-agnostic agentic infrastructure for Salesforce developer experience tooling
A transactional execution harness for AI coding agents with evidence-backed reports.
<!-- test preview system --> <p align="center"> <h1 align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://pullfrog.com/frog-white-200px.png"> <img src="https://pullfrog.com/frog-green-200px.png" width="25
CLI + stdio MCP + library SDK for the Unfairly multiplayer context layer — sync vaults, run agents, emit events
Coding agent CLI with read, bash, edit, write tools and session management