Search

Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating...

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...

Log every LLM API call with full request/response for Hermes Agent

Track per-request LLM token consumption for Hermes Agent

Open-source local AI client and coding agent for DeepSeek, Qwen, ChatGPT and EconomyOS with memory, voice, browser tools, OpenAI/Anthropic-compatible APIs and VS Code.

Agent-native, governed AI runtime for Rust, Python, and TypeScript — native providers, MCP, tools, routing, memory, budgets, audit, and containment.

Open-source AI coding agent for your terminal — one Rust binary, 15+ LLM providers, 1,000+ models. A self-hostable Claude Code / Codex CLI alternative (MIT).

Discord meeting bot: local Whisper transcription, LLM summarization, and an agent that tracks tasks/decisions as searchable memory across meetings.

General-purpose agent with transport abstraction, state management, and attachment support

Sema Server — the server/API implementation layer for Sema, wiring core, registry, model providers, and cloud agent execution. Built on @sema-agent/core.

Run the Codex CLI non-interactively from Python, backed by a Rust core.

A near-zero-dependency, fault-tolerant multi-agent framework built on Stigmergy, Latent State Transfer, and a Byzantine-inspired consensus quorum.

Shared chassis for agent-ready CLIs: the exit-code contract, JSON/table/markdown/CSV output with field projection, and keyring-backed credentials.

SDK for building Holokai neurons in Python — connect to a BigBrain gateway over HTTP+SSE and execute capability-typed tasks.

yothere is the hands-free cockpit for your AI coding agents (Claude Code and Codex): the fleet runs unattended on your own machine, yothere routes only the decisions that need a human, and you answer by voice or one tap, wherever you are.

A production-oriented Python rebuild of Claude Code — real architecture, reliable CLI agent

CODEC-CORTEX — Universal Communication Protocol for LLM/SLM Agents. Compresses agent knowledge via deterministic sigil codec with semantic learning engine (SES→LNG→KNW).

A declarative language for LLM-driven state machines (reference interpreter).

Micro-framework for building A2A agents with LiteLLM — agent loop, tool registry, A2A gateway.

Adaptive failure-mode taxonomy runtime for Codex, Claude Code, and custom agent harnesses.