Forge is a secure, portable AI Agent runtime. Run agents locally, in cloud, or enterprise environments without exposing inbound tunnels.

L0: The Missing Reliability Substrate for AI. Streaming-first. Reliable. Replayable. Deterministic. Multimodal. Retries. Continuation. Fallbacks (provider & model). Consensus. Parallelization. Guardrails. Atomic event logs. Byte-for-byte replays.

Unified Local AI Interface & LLM Runtime (Support GGUF, Ollama, OpenAI, Gemini, etc.). Insearch of building sovereign AI system ✨

LLM agent runtime with paged virtual memory and spatial context awareness

L0: The Missing Reliability Substrate for AI. Streaming-first. Reliable. Replayable. Deterministic. Multimodal. Retries. Continuation. Fallbacks (provider & model). Consensus. Parallelization. Guardrails. Atomic event logs. Byte-for-byte replays.

Production-grade TypeScript AI runtime focused on reliability, governance, and reproducible LLM systems. Multi-provider gateway, agents, RAG, workflows, policy engine, audit trails, and deterministic testing — built for teams shipping AI in production.

Multi-provider LLM runtime core: routing, key management, and resilient fallback execution for agent orchestration.

mindscript-runtime is the minimal, reference implementation of the MindScript engine. It provides: - a CLI for running .ms / .ms.md files - a parser that converts MindScript into an internal AST - a stage-based runtime that executes each stage sequentially - adapters for different LLM backends (OpenAI, Gemini, local stub)

Agent memory runtime: short/long-term context, vector persistence, compression, and personalization primitives.