agent-runtime

Local-first project-aware coordination runtime for ChatGPT, Claude Code, Hermes, durable tasks, tools, research, evidence, and continuity.

A model-agnostic, fail-closed agent runtime — the portable chassis your agent runs on. Source-available.

A verification-first runtime for AI web agents — with Jest-style assertions and token-efficient snapshots

Provider-neutral TypeScript contracts for hosting coding agents.

Aether — model-led execution runtime for autonomous computer work. Make the model the limit.

A production-ready runtime for autonomous AI agents

Runtime kernel for PLATO — the AI theorem prover. Conservation-verified computation on bare metal.

ClawFlow: A lightweight Agent Runtime / AgentOS Kernel for next-generation personal AI agents

wepchat 可能是“又一个” flutter 大模型聊天客户端， 也可能是 “纯dart ai agent范例”

JIT-JEV Context OS for Agent Zero — Epistemic runtime, JEV System 1 decision gate, 3-tier memory cascade (L0/L1/L2) & prompt-caching optimization

A local Rust agent harness with a meta-harness

Composable agent framework with trait-based architecture and production HTTP runtime

Provider-neutral, No-PTY, embeddable Agent Execution SDK.

Production-grade Rust runtime for multi-agent AI systems. Orchestrate LLM agents, skills, and DAG workflows with native Python and Rust SDKs.

A local-first, governed runtime and MCP server for turning repositories, software, and data into agent-native worlds.

Build agents with any framework. Ship them with FastAgentic.

x404-r is database-native infrastructure for crash-proof AI agents. Built on CockroachDB, it transforms your database into a durable runtime where agent state survives any failure.

A safety-oriented AI Agent runtime with isolated sessions, auditable tools, approval gates, Skills, MCP, and Cron execution.

Proof of work in agent runtime behavior, CLI update flows, and CI reliability.

Local AI gateway with OpenAI-compatible chat, universal task APIs, scoped auth, egress policy, and durable task ownership.