A free MIT AI gateway that exposes hundreds of providers and models through one OpenAI-compatible endpoint, with quota-aware fallback, token compression, routing strategies and MCP/A2A support.cheaper-inference
A DeepSeek Harness plugin that adds free and bring-your-own-key model providers, a local OpenAI/Anthropic-compatible gateway, routing, usage dashboards, and token compression.Ebony-Vinyl
This DeepSeek Harness plugin adds free, no-key access to several upstream model pools and exposes a local OpenAI/Anthropic-compatible gateway. It includes fallback routing, usage dashboards, token-saving compression and in-app updates.zouyuxuan122
T3 Code is a remote control surface for the coding agents already installed on your machine, letting you drive Claude Code, Codex, Cursor and others from mobile, web or desktop.pingdotgg
A terminal runtime and workspace manager for coding agents, keeping sessions alive across detaches, organizing multiple machines, and exposing panes to agents through a CLI and socket API.herdrdev
A pure-C inference engine that runs giant mixture-of-experts models on everyday hardware by streaming experts from disk with OpenAI-compatible serving.justvugg
An independent auditing tool for AI agents that simulates realistic business requests and grades responses, surfacing misalignment, privilege abuse, prompt injection, and other risks in a scored report.ifixai-ai
A local model gateway and control plane for coding agents such as Claude Code, Codex and OpenCode, unifying providers, routing, credentials, tools and request observability.musistudio
A local gateway and menu-bar app that lets any coding agent use any model or subscription, with unified provider management, failover, profiles and privacy masking.yetone
A desktop account manager and protocol proxy for AI services, offering one-click multi-account switching, quota monitoring, and OpenAI/Anthropic/Gemini-compatible endpoints for coding agents.lbjlaq
NVIDIA's open-source reference stack for running AI agents such as OpenClaw and Hermes safely inside OpenShell sandboxes, with managed inference, network policies, state persistence, and lifecycle operations.nvidia
Wasmer is a fast, lightweight WebAssembly sandbox runtime and CLI with SDKs for JavaScript, Python, Rust and Swift, letting you run portable or untrusted code safely across local, cloud and browser environments.wasmerio
A cross-platform desktop utility for managing accounts across AI IDEs such as Codex, Cursor, Copilot, Windsurf, and Antigravity, with quota monitoring, one-click switching, wake-up tasks, and parallel instances.jlcodes99
DeepEval is an open-source LLM evaluation framework with Pytest-style testing, diverse judge metrics, synthetic datasets, and tracing for agents and RAG pipelines.confident-ai
opencodex is a local AI gateway that lets Codex, Claude Code, Claude Desktop, and Grok Build use many model providers, with routing, account pooling, and a management dashboard.lidge-jun
FreeToken is an edge-native Mixture-of-Experts inference engine that runs large open-weight models on consumer hardware, with a desktop app, CLI, and OpenAI/Anthropic-compatible APIs.flashml-org
AG-UI is an open, event-based protocol that standardizes how AI agents connect to user-facing applications, shipping SDKs, middleware and a reference HTTP implementation for agent-powered frontends.ag-ui-protocol
An Obsidian plugin that embeds Claude Code, Codex, OpenCode and other coding agents in your vault, with sessions, inline editing, skills, and cross-session messaging.YishenTu
An open-source web and mobile UI for Claude Code, Cursor CLI, and Codex, letting you manage coding-agent sessions, files, Git, and MCP from anywhere.siteboon
Google's declarative runtime for running autonomous agent workloads at scale on Kubernetes, sandboxing each task and pre-wiring repositories, tools and models.google
A highly customizable status line for the Claude Code CLI that shows model, Git branch, token usage, cost, and limits in real time, with themes and Powerline styling.sirmalloc
An open-source AI gateway that routes requests across 1600+ LLMs with retries, guardrails, caching, observability, and MCP server management.Portkey-AI
A desktop, web, VS Code, and mobile workspace for running and reviewing OpenCode coding-agent sessions, with goals, multi-run comparison, previews, GitHub workflows, and private remote access.openchamber
Arize Phoenix is an open-source observability and evaluation platform for LLM applications, offering OpenTelemetry tracing, datasets, experiments, prompt management, and LLM-based evals.Arize-ai
Official developer inspector for MCP servers with web, CLI and TUI clients to connect, list tools, call methods and smoke-test servers.modelcontextprotocol
Tyk is a cloud-native open-source API and AI gateway supporting REST, GraphQL, gRPC, TCP, and MCP, adding authentication, rate limiting, analytics, and governance for API and AI-agent traffic.TykTechnologies
An operating-system-grade runtime for AI agents that runs WebAssembly capsules with capability security, sandboxing, isolation, and auditable execution.unicity-astrid
Pixel Agents turns AI coding agents running in your terminals into animated pixel-art characters in a tiny office, showing what each agent is doing and letting you launch and manage sessions.pixel-agents-hq
Bifrost is a high-performance AI gateway that unifies 23+ providers behind one OpenAI-compatible API. It adds automatic failover, load balancing, semantic caching, guardrails, governance, and observability, with a web UI and Docker deployment.maximhq
Atlas is an agent visibility and control layer that records coding agent sessions, links them to commits, and gives teams a shared timeline, memory, and usage dashboard.tryatlas
Claude Code Usage Monitor is a terminal companion that tracks Claude Code token, message, and cost usage in real time, with forecasting, warnings, and machine-readable exports.Maciek-roboblog
An open-source OpenAI-compatible API server that unifies models, vector search, and agentic orchestration as infrastructure for AI applications anywhere with pluggable providers.ogx-ai
An open agent operating system that gives AI agents a governed local environment for tools and permissions, running capabilities as isolated WebAssembly capsules.unicity-aos
A local browser UI for the pi coding agent that reuses pi's config and session files to browse and resume sessions, run agent turns, configure models, and inspect project files.agegr
A lightweight C/C++ diffusion-model inference engine built on ggml, supporting Stable Diffusion, FLUX, Wan, Qwen Image, and other image and video models on local CPU or GPU backends.leejet
A multi-account Grok API gateway exposing OpenAI- and Anthropic-compatible endpoints, with account pools, routing, auditing, and an admin console.chenyme
An open-source local inference engine tuned for each machine that runs open models quickly and connects them to popular coding agents via compatible APIs.magnitudedev
vLLM-Omni extends vLLM to serve omni-modality models, supporting text, image, audio, video, and action generation with an OpenAI-compatible API, streaming, and distributed inference.vllm-project
An open-source LLM gateway that unifies API keys, subscriptions, and local models behind one OpenAI-compatible endpoint, adding routing, fallbacks, full logs, and cost tracking.mnfst