Search

Cross-framework AI agent observability and reliability shim

LangGraph.js checkpoint saver for Cloudflare D1

Drop-in AI agent controlled via Telegram, sandboxed to its folder

Ephemeral coding-agent runner: orchestrates Pi CLI via Docker for automated code modifications with validation

Placeholder package. The real release is coming soon.

Agent-operated developer-experience CLI — deterministic per-backend markdown briefings for autonomous agents.

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7

Secure remote tmux session connector for Claude Code, Codex, and terminal agents.

Adaptive Utility Agents — a Django-like framework for adaptive multi-model LLM systems.

CrewAI tool for the Ejentum Reasoning Harness. Each call retrieves a task-matched cognitive operation engineered in two layers: a natural-language procedure plus an executable reasoning topology (graph DAG with gates, parallel branches, and meta-cognitive exits). Injected before the LLM step to harden reasoning against decay on complex tasks and long agent loops.

Fetch X/Twitter tweets, replies, timelines, and articles without login or API keys — field tool for AI agents.

Agent Waystation · Agent 驿站 — a stopover for AI agents, builders, tools, and field reports

AI-Powered Offensive Security Research Engine - desktop-native security testing platform with native MCP integration. 69 tools, MITM proxy, stealth browser, autonomous AI agent. Built on Tauri + Rust + React.

Small TUI coding agent in Go for any OpenAI-compatible endpoint. Built-in read/write/edit/bash/grep/web_fetch tools, sandboxed shell, SQLite session persistence.

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

LLM-friendly JSON-based presentation engine

Orchestrate a cluster of containerized local LLMs (via Ollama), each with a specific persona and role, that collaborate to solve a goal.

EasyObs SDK: lightweight LLM/agent observability instrumentation via OpenTelemetry

Install the Parley Deck vendor-neutral AI cooperation skill into local AI agent runtimes or a custom skill directory.

Git-native CLI for syncing AI agent skills across environments.