Search

Open-source voice AI SDK — connect any AI agent to real phone calls in 4 lines of code

Local-first CLI that gives AI agents persistent, curated memory

Multi-agent coordination protocol for AI coding tools

Core agent runtime for the [rill](https://github.com/rcrsr/rill) language. Loads agent manifests, builds an `AgentRouter`, and serves agents over HTTP via the included Hono harness. Supports single-agent and multi-agent deployments.

Give AI agents the ability to edit their own context window

Agent runtime with tool calling and state management. Coming soon.

Auto-learning codebook compression for AI agent memory. Makes context files 2-10x smaller while staying LLM-readable.

Stealth browser instrument for AI agents. Real Chrome + patchright CDP stealth + human-calibrated behavioral simulation. Every action is indistinguishable from a human.

A Claude Code-style coding agent for your terminal — runs on local LLMs via Ollama or cloud APIs

AutoGen code executor for Sandflare Firecracker microVM sandboxes — run agent-generated code safely

CrewAI tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely

LangChain tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely

LlamaIndex tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely

Repo-native runtime contract and context bootstrapper for coding agents

A web UI for managing Claude Code's harness, persona, and settings.

One local callback layer for Claude Code and Codex: a macOS-ready CLI for native permission dialogs and notifications, plus a FastAPI-like Python framework

Governance and evidence layer for multi-agent AI decision arbitration

One More Dimension — lightweight LLM agent framework with tool-calling, skills, and file tools

A Zero-Trust validation and telemetry toolkit for multi-agent workloads.

AI model: AgentAnon/gemma-4-it-GGUF-WITH_mmproj_VisionFiles