nshkr-ai-infra

A practical, multi-layered JSON repair library for Elixir that intelligently fixes malformed JSON strings commonly produced by LLMs, legacy systems, and data pipelines.

Elixir RAG library with multi-LLM routing (Gemini, Claude, OpenAI, Ollama), GraphRAG, knowledge graphs, modular retrievers/rerankers, composable pipelines, pgvector integration, advanced chunking, and tool-using agents. Fork of bitcrowd/rag.

High-performance, generalized process pooler and session manager for external language integrations. Orchestrates and supervises languages like Python and Javascript from Elixir.

Compile-time Elixir code generator for Python library bindings. Declare dependencies in mix.exs, generate type-safe modules with introspected typespecs and docs. Deterministic git-friendly output, strict CI mode, streaming, and custom helpers. Runtime via Snakepit.

Elixir implementation of GEPA: LLM-driven evolutionary optimization using Pareto-efficient search for text-based systems. Features OpenAI/Gemini integration, BEAM concurrency, OTP supervision, 218 tests with 75% coverage.

Elixir port of tinker-cookbook: training and evaluation recipes for the Tinker ML platform.

Unified API gateway for the NSAI ecosystem—authentication (JWT, API keys, OAuth2/OIDC), distributed rate limiting with burst allowance, circuit breakers, request tracing, Prometheus metrics, and service proxying. Production-ready with comprehensive observability and multi-tenant support.

Hexagonal architecture core for Elixir RAG systems. Port specifications, manifest-based config, adapter registry, and DI framework. Enables swappable vector/graph/embedding/LLM backends via clean port/adapter abstractions. Hex.pm publishable.

Core Elixir library for AI agent orchestration - unified workbench for running, tracking, and orchestrating multi-provider LLM agents with sessions, workflows, RAG indexes, tool approvals, and cost tracking

Elixir SDK for the Tinker ML platform—LoRA training, sampling, and service orchestration built on OTP, Finch, and telemetry.

Execution Plane is an Elixir/OTP runtime substrate for boundary-aware AI infrastructure, unifying process execution, protocol framing, transport lifecycle, realtime streams, JSON-RPC control lanes, and future sandbox-backed placement under one composable kernel for agentic systems.

Lightweight Elixir runtime for composing and executing Python-backed data pipelines with automatic dependency resolution, lazy evaluation, fault-tolerant stage supervision, and seamless Snakebridge/Snakepit integration for production-grade cross-language AI and scientific computing workflows on the BEAM.

Reusable GEPA optimizer framework for typed candidate generation, evaluation, persistence posture, tracing contracts, and deterministic prompt optimization infrastructure.

Service discovery and registry for the NSAI ecosystem—distributed registry with health checking, circuit breakers, multiple storage backends (ETS/PostgreSQL), PubSub event broadcasting, and comprehensive telemetry. Built on OTP with Horde-ready architecture for multi-node deployments.

Reusable TRINITY router and coordination framework for deterministic agent routing, provider pool contracts, typed coordination patterns, and local-first AI infrastructure.

Claude Skill Aggregator

The command and control layer for the AI-powered enterprise

Reusable Elixir semantic inference contracts, adapters, trace metadata, and conformance tests for local CLI agents, hosted model SDKs, and governed nshkr runtime integration.

Pure Elixir TikToken-style byte-level BPE tokenizer (Kimi K2 compatible).

Shared lower infrastructure monorepo for the nshkr platform core: contracts, Postgres durability helpers, projection publication glue, lease and fence primitives, replay-safe ids, and common runtime infrastructure used by outer_brain, Citadel, jido_integration, and app-facing surfaces.