Agent OS: Stop prompting. Start specifying.
-
Updated
Jun 9, 2026 - Python
#
llm-runtime
Here are 18 public repositories matching this topic...
Forge is the open-source runtime for Anthropic's Agent Skills standard — built for the agent that runs next to a service, in your environment, on infrastructure you already operate. Write a SKILL.md. Compile to a portable, hardened agent. Deploy it anywhere containers run: Kubernetes, on-prem, air-gapped, embedded in CI, or as an A2A endpoint.
mcp openai ai-agents claude a2a secure-ai local-ai enterprise-ai ai-agents-cli ai-workforce a2a-protocol local-ai-agents llm-runtime portable-agents agent-cli openclaw
-
Updated
Jun 10, 2026 - Go
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.
typescript ai-framework rag agent-framework ai-compliance llm ai-governance ai-runtime open-source-ai ai-infrastructure llm-gateway reproducible-ai llm-runtime ai-reliability deterministic-ai ai-production
-
Updated
Jun 4, 2026 - TypeScript
Browser-based agent platform with a user workspace, admin console, product gateway, and per-user runtime isolation.
-
Updated
Apr 30, 2026 - TypeScript
Unified execution runtime for LLM and ML programs.
machine-learning deep-learning transformers pytorch agents execution-engine kv-cache dataflow-graph llm generative-ai ai-runtime workflow-optimization program-optimization prefix-caching agent-runtime llm-runtime compiler-runtime cross-call-caching
-
Updated
May 1, 2026 - C++
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.
streaming typescript ai fault-tolerance sentry pipelines replays fallbacks ai-agents multimodal openai-api llm retry-logic ai-runtime vercel-ai-sdk ai-infrastructure ai-guardrails mastra-ai ai-streaming llm-runtime
-
Updated
Jun 9, 2026 - TypeScript
Inference-aware runtime for AI coding agents that reuses execution state to reduce repeated reasoning, repo rereads, tool calls, and failure loops.
rust compression retrieval memory sqlite summarization lossless dag lcm fts5 llm ai-runtime deepseek agent-runtime context-engineering llm-runtime memory-runtime inference-runtime
-
Updated
Jun 9, 2026 - Rust
Unified Local AI Interface & LLM Runtime (Support GGUF, Ollama, OpenAI, Gemini, etc.). Insearch of building sovereign AI system ✨
ai webui hardware-acceleration rag ai-assistant llm llm-inference ollama gguf llm-webui gemini-sdk openai-compatible gguf-quantization llm-runtime lm-webui
-
Updated
Feb 26, 2026 - Python
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.
python streaming ai fault-tolerance sentry fallback replays fallbacks ai-agents multimodal openai-api llm retry-logic ai-runtime litellm ai-infrastructure ai-guardrails ai-streaming llm-runtime
-
Updated
Jun 3, 2026 - Python
LayerRun is a Rust-based local LLM runtime for memory-aware model execution, layer-wise loading, model inspection, and flexible inference serving.
-
Updated
Jun 8, 2026 - Rust
An LLM agent runtime that treats context like virtual memory: swim-lane paging, semantic retrieval, and an inline stream-marker DSL for runtime control. Multi-provider (Anthropic, OpenAI, Google, xAI, Groq, local). MCP-integrated. Self-modifying agent mode (PLASTIC). Containerized deployment.
mcp multi-agent autonomous-agents ai-agents agent-framework llm long-context ai-runtime llm-agents context-management ai-infrastructure model-context-protocol agent-runtime llm-runtime
-
Updated
May 17, 2026 - TypeScript
Run any LLM locally. Use it from any language. Deploy anywhere.
nodejs python c go rust cli php machine-learning inference bindings large-language-models llm llama-cpp local-llm gguf openai-compatible-api llm-runtime cognisoc
-
Updated
Jun 6, 2026 - Python
Multi-provider LLM runtime core: routing, key management, and resilient fallback execution for agent orchestration.
python fallback multi-provider provider-registry agent-orchestration llm-runtime model-routing inference-runtime
-
Updated
Apr 10, 2026 - Python
Agent memory runtime: short/long-term context, vector persistence, compression, and personalization primitives.
-
Updated
Apr 10, 2026 - Python
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)
developer-tools ai-framework cli-tool prompt-engineering llm-runtime mindseye mindscript mindscript-runtime
-
Updated
Dec 10, 2025 - Python
Bootable Ubuntu image pre-loaded with LLMs, agent frameworks, and tooling - boot, SSH in, run an agent, zero setup.
-
Updated
Apr 15, 2026 - Python
A modular LLM inference runtime written in Rust.
rust modular inference crates-io rustlang modular-design llm rust-runtime ai-infrastructure llm-runtime cognisoc
-
Updated
Jun 6, 2026 - Rust
codex memory-injection ai-memory agent-memory claude-code context-engineering llm-runtime persistent-context llm-context-compiler multi-model-collaboration
-
Updated
May 1, 2026 - TypeScript
Improve this page
Add a description, image, and links to the llm-runtime topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the llm-runtime topic, visit your repo's landing page and select "manage topics."