#Ai-infrastructure
Showing 44 of 44 repositories tagged #ai-infrastructure, ranked by stars
Open-source context retrieval layer for AI agents
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
14-stage Fusion Pipeline for LLM token compression โ reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
AI Infrastructure Engineer Learning Track - Production ML infrastructure curriculum (2-4 years experience)
Semantica ๐ง โข Build AI systems that can explain, trace, and justify every decision. Knowledge graphs, context graphs, reasoning engines, provenance, and governance for production AI.
๐ก๏ธThe governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.
Local-first AI conversation memory hub to capture, search, summarize, and export chats across major AI platforms. ๆฌๅฐไผๅ ็ AI ๅฏน่ฏ่ฎฐๅฟไธ็ฅ่ฏไธญๅฐใ
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.
Governed shared memory for AI agent fleets โ multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Open-source protocol suite standardizing LLM, Vector, Graph, and Embedding infrastructure across LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, and MCP. 3,330+ conformance tests. One protocol. Any framework. Any provider.
Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It auto injects relevant memories across developers and future sessions to save tokens and time spent on tasks.
AI Infrastructure Junior Engineer Learning Track - Comprehensive curriculum for entry-level ML infrastructure engineers (0-2 years experience)
Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternative.
Plug-and-play homelab dashboard in one container โ GPU, local-AI VRAM, Docker, systemd, host health. Built-in read-only MCP server so AI agents can explore it too.
A local workbench for agents doing continuous work across sessions, commands, human input, and external events.
The open source, no-code MCP Server for AI-Native API Access
ๅฏๆบๅนณๅฐไปปๅก็ฎก็ CLI๏ผ่ตๆบๆฅ่ฏขใไปปๅกๆไบคใๆฅๅฟๆฅ็ๅ MCP/agent workflow
KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required
Local coding-agent orchestrator โ DAG of auto-approved, git-worktree-isolated sub-sessions across LLM providers (Claude/Kimi/Grok/DeepSeek/local). AGPL-3.0.
Route inference across providers.
Context Runtime โ a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused substrate, and learns from the outcome.
Distributed data mesh for real-time access, migration, and replication across diverse databases โ built for AI, security, and scale.
โ๏ธ Kubernetes-Native Database-Driven Provisioning Workflow Automation
Portable AI runtime inspired by docker-compose. Compose agents, RAG pipelines, and MCP servers in one YAML file and run them anywhere.
Predictive memory layer for AI agents. MongoDB + Qdrant + Neo4j with multi-tier caching, custom schema support & GraphQL. 91% Stanford STARK accuracy, <100ms on-device retrieval
Open-source AI agent runtime built in Rust. Define once, deploy isolated instances per tenant with built-in memory, encrypted vault, self-extending skills, cron, and multi-channel support.
Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment
The living armor an AI agent inhabits: eternal devouring, eternal evolution, eternal amplification.
AI SRE tools for RCA, Incident Response, Cost-Saving, Infra management, DevOps and more
Zero-code LLM security & observability proxy. Real-time prompt injection detection, PII scanning, and cost control for OpenAI-compatible APIs. Built in Rust.
Stop paying for AI APIs during development. LocalCloud runs everything locally - GPT-level models, databases, all free.
Stateless LLM runtime that dynamically routes, loads, executes, and unloads models per request with bounded VRAM caching and intelligent model selection.
AI Infrastructure Performance Engineer Learning Track - GPU optimization, inference optimization, and cost reduction
TME: Structured memory engine for LLM agents to plan, rollback, and reason across multi-step tasks.
Runtime economic governance for AI agents. Circuit Breaker adds risk-managed execution, cost ceilings, and kill switches to autonomous AI workflows.
Production-ready AI infrastructure: RAG with smart reindexing, persistent memory, browser automation, and MCP integration. Stop rebuilding tools for every AI project.
Multi-model AI agent runtime. Define agents in YAML, connect 6 LLM providers, orchestrate with ReAct/Plan&Execute/Fan-Out/Pipeline/Supervisor/Swarm patterns, and deploy as REST/WebSocket API with RAG, memory, MCP tools, guardrails, and OpenTelemetry observability.
Deploy intelligence. Open-source infrastructure for AI agents in production.
Your machine's AI brain. One 20MB binary gives every tool, script, and cron job shared AI memory + 136 API endpoints. Desktop app, CLI, Telegram โ all connected. Rust-powered.
๐ค Official Interactive Tutorial for OpenHarness โ Zero to Hero in 12 Chapters | Learn OpenHarness like Claude Code: Agent Loop, Tools, Memory, Multi-Agent | ้ขๅ้ถๅบ็ก็ AI Agent ไบคไบๅผๆ็จ
Pause your AI agent. Ask a human. Resume with their answer. Open source human-in-the-loop (HITL) library for production LLM agents: Slack, email, and web dashboard. Typed Pydantic and Zod responses. Durable Temporal and LangGraph adapters. AI verifier. Audit trail. Self-hosted, Apache 2.0. Python and TypeScript.
The meta-architecture behind a high-leverage Claude Code setup. Installed by the very tool it optimizes.
Kubernetes scanner that discovers LLMs running on vLLM and extracts their deployment and runtime facts.
Hybrid RAG (DuckDB vector + BM25 + RRF + recency/keyword priors + optional cross-encoder rerank) as an installable library + CLI.