Governed AI execution
as a typed platform stack.
The system is split by ownership. app_kit is the product
boundary and northbound API. mezzanine owns reusable
operational truth: packs, lifecycle, execution, decisions, evidence,
projections, reviews, archival posture, and Temporal handoff.
outer_brain owns semantic context and memory recall.
citadel owns authority, policy, and governance compilation.
jido_integration is the durable Spine for Brain ingress,
lower facts, leases, review truth, and connector admission.
execution_plane is the hazmat layer for raw runtime mechanics.
Technical deep dive
The stack is not a loose brand diagram. It is a set of typed handoffs, durability boundaries, and proof surfaces. Product code does not stitch lower services together directly. It enters through AppKit, which exposes stable DTOs and governed surfaces. Mezzanine turns product intent into substrate records. Brain-side packages shape semantic meaning and authority. The Spine accepts or rejects lower work, records facts, and mediates reads. Execution Plane performs raw effects behind explicit receipts. Stack Lab, AITrace, release manifests, schema registries, and no-bypass scans provide the proof surface.
app_kit is the workspace product code is allowed to touch
for governed platform behavior. It carries chat, typed domain,
operator, work-control, runtime gateway, review, installation,
semantic assist, trace lookup, and leased lower-read surfaces. It is
also the enforcement point: product and hazmat scanner profiles reject
direct imports into Mezzanine runtime services, Citadel internals, Jido
Integration, and Execution Plane unless the product is authoring a pure
Mezzanine.Pack model contract.
mezzanine is the neutral high-level monorepo behind
AppKit. It owns pack registration, compiled installation config,
source admission, subject and object lifecycle, execution ledgers,
decision and review state, evidence, projections, audit, archival
restore posture, operator actions, runtime scheduling, and Temporal
workflow handoff. Oban remains a local delivery and garbage-collection
tool where explicitly retained; Temporal owns active workflow
lifecycle, while Postgres stores substrate truth and projection facts.
outer_brain owns semantic session work: context assembly,
clarification, memory-shaped recall, normalized semantic outcomes,
semantic failure journaling, and AITrace-linked provenance.
citadel owns authority and policy compilation before
mutation: action requests, capability posture, governance packets,
topology, and the authorization shape that lower layers must receive.
The split is deliberate: cognition can be rich, but durable mutation
still needs deterministic authority.
jido_integration is the Spine. It accepts Brain-origin
work, validates ingress shape, owns auth and lease lifecycle, records
review and control-plane truth, admits connectors, publishes connector
effects, and exposes lower facts through tenant-scoped substrate reads.
It is not just a connector workspace; it is the durable middle layer
between Brain governance and raw execution mechanics.
execution_plane owns low-level effect mechanics: HTTP,
process, JSON-RPC, placement, sandbox and operator-terminal lanes, plus
future cell-style execution. Provider and runtime-family kits such as
Pristine, Prismatic, CLI Subprocess Core, and Agent Session Manager
normalize transport and session behavior. They emit receipts and raw
facts; they do not own product truth, semantic meaning, or review
state.
The memory architecture extends the same contract discipline into
recall. Platform.AccessGraph.v1 makes user, agent,
resource, scope, policy, and review-authority relations epoch-stamped.
Private, shared, and governed memory live in separate stores with
different writers and constraints. Share-up and promotion create new
fragments, preserve parent links, apply transform policy, and emit
proof tokens so a future audit can answer which memories influenced a
decision, under which policy, and whether those fragments would still
be admissible now.
Typed ingress before side effects
Product calls enter through app_kit with request context, tenant and installation refs, idempotency, trace, and typed DTOs. Mezzanine turns that into substrate records. Citadel compiles authority. Jido Integration accepts or rejects lower ingress. Execution Plane only sees shaped runtime intent, never product shortcuts.
Durability belongs to the owner
mezzanine records operational ledgers, workflow handoff, reviews, projections, audit, and archival evidence. jido_integration records lower facts, leases, connector admission, and review-adjacent Spine truth. execution_plane records raw runtime receipts. Recovery logic is attached to the layer that can actually replay or repair the fact.
Proof is part of the contract
stack_lab scenarios, AITrace spans, schema registries, release manifests, no-bypass scans, projection hashes, proof tokens, and retrospective audits are not documentation after the fact. They are how the platform proves recall, promotion, dispatch, operator review, tenant scoping, version skew, and boundary discipline under failure.
All Repositories
View on GitHub →
synapse
Headless, declarative multi-agent orchestration …
★ 44
flowstone
Asset-first data orchestration for Elixir/BEAM. …
★ 27
DSPex
Declarative Self Improving Elixir - DSPy Orchestration …
★ 18
ds_ex
DSPEx - Declarative Self-improving Elixir | A …
★ 17
ALTAR
The Agent & Tool Arbitration Protocol
★ 8
mabeam
Multi-agent systems framework for the BEAM platform - …
★ 8
pipeline_ex
Claude Code + Gemini AI collaboration orchestration …
★ 8
jido_hive
Phoenix coordination server and embeddable Elixir …
★ 2
flowstone_ai
FlowStone integration for altar_ai - AI-powered data …
★ 1
synapse_ai
Synapse integration for altar_ai - SDK-backed LLM …
★ 1
extravaganza
First proving-ground product app for the nshkr stack: a …
mezzanine
Neutral high-level reusable monorepo for the nshkr …
stack_coder
An advanced Elixir-based AI coding agent focused on …
gemini_ex
Elixir Interface / Adapter for Google Gemini LLM, for …
★ 31
claude_agent_sdk
An Elixir SDK for Claude Code - provides programmatic …
★ 30
codex_sdk
OpenAI Codex SDK written in Elixir
★ 19
agent_session_manager
Agent Session Manager - A comprehensive Elixir library …
★ 8
ollixir
Ollixir provides a first-class Elixir client with …
★ 5
altar_ai
Protocol-based AI adapter foundation for Elixir - …
★ 4
jules_ex
Elixir client SDK for the Jules API - orchestrate AI …
★ 2
notion_sdk
Native Elixir SDK for the Notion API — comprehensive, …
★ 2
amp_sdk
Elixir SDK for the Amp CLI — provides a comprehensive …
★ 1
github_ex
Native Elixir SDK for the GitHub REST API — …
★ 1
mcp_client
Full-featured Elixir client for the Model Context …
★ 1
vllm
vLLM - High-throughput, memory-efficient LLM inference …
★ 1
cli_subprocess_core
Foundational Elixir runtime library for deterministic …
crucible_prompts
Prompt and parsing utilities for Crucible and NSAI. …
external_runtime_transport
An Elixir-first external runtime transport foundation …
gemini_cli_sdk
An Elixir SDK for the Gemini CLI — Build AI-powered …
linear_sdk
Elixir SDK for Linear built on Prismatic, using a …
llama_cpp_sdk
Barebones Elixir wrapper and integration surface for …
nsai_llm
Shared LLM Actions for NSAI runtimes. Wraps …
self_hosted_inference_core
Core Elixir primitives for building reliable …
json_remedy
A practical, multi-layered JSON repair library for …
★ 31
snakepit
High-performance, generalized process pooler and …
★ 11
rag_ex
Elixir RAG library with multi-LLM routing (Gemini, …
★ 9
snakebridge
Compile-time Elixir code generator for Python library …
★ 8
gepa_ex
Elixir implementation of GEPA: LLM-driven evolutionary …
★ 3
tinkex_cookbook
Elixir port of tinker-cookbook: training and evaluation …
★ 3
portfolio_core
Hexagonal architecture core for Elixir RAG systems. …
★ 2
slither
Lightweight Elixir runtime for composing and executing …
★ 2
tinkex
Elixir SDK for the Tinker ML platform—LoRA training, …
★ 2
command
Core Elixir library for AI agent orchestration - …
★ 1
execution_plane
Execution Plane is an Elixir/OTP runtime substrate for …
★ 1
nsai_gateway
Unified API gateway for the NSAI …
★ 1
nsai_registry
Service discovery and registry for the NSAI …
★ 1
nsai_work
NSAI.Work - Unified job scheduler for North-Shore-AI …
★ 1
pilot
Interactive CLI and REPL for the NSAI ecosystem—unified …
★ 1
skill_ex
Claude Skill Aggregator
★ 1
tiktoken_ex
Pure Elixir TikToken-style byte-level BPE tokenizer …
★ 1
app_kit
Shared app-facing surface monorepo for the nshkr …
ground_plane
Shared lower infrastructure monorepo for the nshkr …
hf_hub_ex
Elixir client for HuggingFace Hub—dataset/model …
hf_peft_ex
Elixir port of HuggingFace's PEFT (Parameter-Efficient …
inference
Reusable Elixir semantic inference contracts, adapters, …
outer_brain
Semantic runtime above Citadel for raw language intake, …
portfolio_index
Production adapters and pipelines for PortfolioCore. …
portfolio_manager
AI-native personal project intelligence system - …
stack_lab
Local distributed-development harness and proving …
tinkerer
Chiral Narrative Synthesis workspace for Thinker/Tinker …
dexterity
Code Intelligence: Token-budgeted codebase context for …
★ 4
elixir_dashboard
A Phoenix LiveView performance monitoring dashboard for …
★ 3
blitz
Small parallel command runner for Elixir and Mix …
★ 1
elixir_tracer
Local-first observability for Elixir with New Relic API …
★ 1
pristine
Shared runtime substrate and build-time bridge for …
★ 1
prompt_runner_sdk
Prompt Runner SDK - Elixir toolkit for orchestrating …
★ 1
weld
Deterministic Hex package projection for Elixir …
★ 1
atlas_once
Atlas Once is a filesystem-first personal memory system …
coolify_ex
Generic Elixir tooling for triggering, monitoring, and …
portfolio_coder
Code Intelligence Platform: Repository analysis, …
prismatic
GraphQL-native Elixir SDK platform and monorepo for …
superlearner
OTP Supervisor Educational Platform
★ 8
apex
Core Apex framework for OTP supervision and monitoring
★ 4
apex_ui
Web UI for Apex OTP supervision and monitoring tools
★ 4
arsenal
Metaprogramming framework for automatic REST API …
★ 4
arsenal_plug
Phoenix/Plug adapter for Apex Arsenal framework
★ 3
foundation
Elixir infrastructure and Observability Library
★ 12
AITrace
The unified observability layer for the AI Control …
★ 2
citadel
The command and control layer for the AI-powered …
★ 1
telemetry_reporter
Pachka-powered telemetry reporter for Elixir that …
★ 1
lineage_ir
Lineage IR for cross-system traces, spans, artifacts, …
duckdb_ex
DuckDB driver client in Elixir
★ 2
ex_topology
Pure Elixir library for graph topology, TDA, and …
★ 2
weaviate_ex
Modern Elixir client for Weaviate vector database with …
★ 2
embed_ex
Vector embeddings service for Elixir—multi-provider …
★ 1
nx_penalties
Composable regularization penalties for Elixir Nx. …
trinity_coordinator
TRINITY in Elixir (An Evolved LLM Coordinator): route …
★ 2
cns
Chiral Narrative Synthesis - Dialectical reasoning …
★ 1
EADS
Evolutionary Autonomous Development System
anti_agents
Anti Agents - Inspired by Sakana AI's String Seed of …
cns_ui
Phoenix LiveView interface for CNS dialectical …
LlmGuard
AI Firewall and guardrails for LLM-based Elixir …
★ 9
ExFairness
Fairness and bias detection library for Elixir AI/ML …
★ 1
crucible_examples
Interactive Phoenix LiveView demonstrations of the …
★ 1
ExDataCheck
Data validation and quality library for ML pipelines in …
cns_crucible
crucible_adversary
Adversarial testing and robustness evaluation for the …
crucible_bench
Statistical testing and analysis framework for AI …
crucible_datasets
Dataset management and caching for AI research …
crucible_deployment
ML model deployment for the Crucible ecosystem. vLLM …
crucible_ensemble
Multi-model ensemble voting strategies for LLM …
crucible_feedback
ML feedback loop management for the Crucible ecosystem. …
crucible_framework
CrucibleFramework: A scientific platform for LLM …
crucible_harness
Experimental research framework for running AI …
crucible_hedging
Request hedging for tail latency reduction in …
crucible_ir
Intermediate Representation for the Crucible ML …
crucible_kitchen
Industrial ML training orchestration - backend-agnostic …
crucible_model_registry
ML model registry for the Crucible ecosystem. Artifact …
crucible_telemetry
Advanced telemetry collection and analysis for AI …
crucible_trace
Structured causal reasoning chain logging for LLM …
crucible_train
ML training orchestration for the Crucible ecosystem. …
crucible_ui
Phoenix LiveView dashboard for the Crucible ML …
crucible_xai
Explainable AI (XAI) tools for the Crucible framework
datasets_ex
Dataset management library for ML experiments—loaders …
eval_ex
Model evaluation harness for standardized …
hf_datasets_ex
HuggingFace Datasets for Elixir - A native Elixir port …
metrics_ex
Metrics aggregation and alerting for ML …
training_ir
Training IR for reproducible ML jobs across Crucible …