awesome jev projects / system-1 architecture radar

Leave thinking to LLMs, delegate decisions to Jev.

Inspect verified open source codebases to see where Jev sits in production Agent loops. Curated 330+ projects spanning browser automation, model routing, MCP servers, and guardrails.

Indexed Projects

333

Categories

17

Tags

20

Source Evidence

100%

Verified & regularly updated
Tactile Inspiration Card

jev-ultrafast by browser-use

A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.

Browser & OS Action6,031
Popular tags:
333 projects matched
langchain repository icon by langchain-ai

langchain-ai

langchain

146,634
SDK & IntegrationsMITPython

An optional Jev classifier integration for Python LangChain workflows.

What Jev does here

Submits binary, categorical and ordered-score questions and returns typed answers with probabilities.

Adds a classification step that can participate in existing LangChain pipelines.

#multilanguage-sdk#classification-ranking
245222 evidence links
Inspect details
63,505
Domain & Vertical ToolsMITPython

An educational AI hedge-fund prototype with an optional Jev adapter for structured judgments in fund decision workflows.

What Jev does here

Converts strategy questions to System One requests and normalizes native answers to the project’s result format.

Allows Jev or other model backends to be used in the same research workflow.

#finance-quant#typed-decisions
111372 evidence links
Inspect details
litellm repository icon by BerriAI

BerriAI

litellm

59,123
Routing & Cost OptimizationMITTypeScript

LiteLLM can use Jev to classify requests for its complexity-based model router.

What Jev does here

Maps requests to configured complexity classes that drive backend routing.

Makes the complexity judgment behind routing inspectable.

#llm-routing-cost#multilanguage-sdk
115694 evidence links
Inspect details
oh-my-pi repository icon by can1357

can1357

oh-my-pi

31,850
Routing & Cost OptimizationMITTypeScript

Oh My Pi includes an optional TypeSafe judgment provider for bounded decisions in coding-agent workflows.

What Jev does here

Sends agent state and typed questions to Jev and parses structured answers.

Adds a replaceable judgment provider to existing agent workflows.

#coding-agents#multilanguage-sdk#typed-decisions
33633 evidence links
Inspect details
30,779
Routing & Cost OptimizationMITPython

A community Claude Code Templates mod that uses Jev to suggest subagent models and reasoning levels.

What Jev does here

Evaluates task tier, reasoning needs and production risk; local policy maps results to invocation settings.

Makes routing rules and per-request choices explicit and configurable.

#llm-routing-cost#coding-agents
34944 evidence links
Inspect details
composio repository icon by ComposioHQ

ComposioHQ

composio

30,238
SDK & Decision FrameworksMITTypeScript

An optional TypeSafe provider for Composio that uses Jev to choose among tools and bounded argument options.

What Jev does here

Turns tool or action conditions into structured questions and passes Jev answers to local invocation logic.

Adds structured judgments to existing tool interfaces.

#multilanguage-sdk#llm-routing-cost#typed-decisions
48062 evidence links
Inspect details
ai repository icon by vercel

vercel

ai

26,835
SDK & Decision FrameworksApache-2.0TypeScript

The TypeSafe provider in AI SDK lets TypeScript applications call Jev through the shared evaluate interface.

What Jev does here

Maps choice, score, and yes/no questions to TypeSafe System One requests and parses typed results.

Reuses a common evaluation interface within AI SDK applications.

#multilanguage-sdk#typed-decisions
51583 evidence links
Inspect details
cua repository icon by trycua

trycua

cua

23,683
Browser & OS ActionMITRust

Cua’s preview jev-use example pairs Driver observation and execution with bounded Jev browser-action choices.

What Jev does here

Reads DOM or supported visual-region descriptions and returns a supplied candidate action ID.

Provides Python and TypeScript loops with separate offline and live checks.

#browser-automation#typed-decisions
16423 evidence links
Inspect details
pydantic-ai repository icon by pydantic

pydantic

pydantic-ai

20,035
SDK & IntegrationsMITPython

An optional TypeSafe provider and Jev model integration for Pydantic AI.

What Jev does here

Converts supported structured output fields into typed Jev questions and maps answers back to the output model.

Lets supported classification outputs use the existing Pydantic AI interface.

#multilanguage-sdk#typed-decisions
27363 evidence links
Inspect details
eliza repository icon by elizaOS

elizaOS

eliza

19,361
SDK & Decision FrameworksMITTypeScript

An optional TypeSafe HTTP adapter in Eliza’s source, not registered with the Agent runtime by default.

What Jev does here

Only an explicit systemOne call sends state and questions, returning validated typed answers.

Provides a reusable server-side module; its presence is not evidence of deployed Jev adoption.

#multilanguage-sdk#typed-decisions
57453 evidence links
Inspect details
langchainjs repository icon by langchain-ai

langchain-ai

langchainjs

18,210
SDK & Decision FrameworksMITTypeScript

An optional LangChain.js TypeSafeClassifier integration for sending state and predefined questions to Jev.

What Jev does here

Uses invoke to call TypeSafe and parse choice, noul, score and probability fields.

Adds typed decisions to LangChain workflows without treating Jev as a chat generator.

#multilanguage-sdk#classification-ranking
33774 evidence links
Inspect details
json-render repository icon by vercel-labs

vercel-labs

json-render

16,572
Creative ToolsApache-2.0TypeScript

A Jev UI-composition experiment inside the json-render website that selects from predefined component and property options.

What Jev does here

Evaluates component configurations through Vercel AI Gateway, then composeSpec assembles the UI specification.

Provides an inspectable composition path alongside token-by-token JSON generation.

#creative-multimedia#typed-decisions
8892 evidence links
Inspect details
openchamber repository icon by openchamber

openchamber

openchamber

10,060
Routing & Cost OptimizationMITTypeScript

OpenChamber’s optional automatic model router uses Jev to classify a message before selecting a configured model and reasoning level.

What Jev does here

Jev selects a task category; local category mappings determine the model configuration.

Keeps routing categories and their model assignments explicit.

#llm-routing-cost#coding-agents
11052 evidence links
Inspect details
rig-typesafeai repository icon by 0xPlaygrounds

0xPlaygrounds

rig-typesafeai

8,669
SDK & Decision FrameworksMITRust

An experimental TypeSafe crate in Rig for expressing Jev questions and answers with Rust types.

What Jev does here

Sends application state and questions to Jev and parses Choice, Score or Noul answers.

Reuses field layouts between questions and answers and validates answers against questions.

#multilanguage-sdk#typed-decisions
9713 evidence links
Inspect details
firstmate repository icon by kunchenguid

kunchenguid

firstmate

6,587
Routing & Cost OptimizationMITShell

Firstmate can optionally use Jev to match task briefs to dispatch rules before local policy chooses an Agent configuration.

What Jev does here

Sends the task brief and candidate rules to Jev, then resolves execution profiles with confidence and local conditions.

Separates semantic matching from the final dispatch policy.

#llm-routing-cost#coding-agents
20072 evidence links
Inspect details
jev-ultrafast repository icon by browser-use

browser-use

jev-ultrafast

6,031
Browser & OS ActionMITPython

A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.

What Jev does here

Chooses an action and its matching DOM element in one request; a text model generates input text.

Separates UI choices, text generation, and browser execution so each step can be inspected.

#browser-automation#typed-decisions
3843 evidence links
Inspect details
agentgateway repository icon by agentgateway

agentgateway

agentgateway

4,926
Security & GuardrailsApache-2.0Rust

A Jev guardrail example in Agentgateway using a webhook to inspect model requests and responses.

What Jev does here

Jev scores jailbreaks, harmful content and secret disclosure; thresholds or evaluation errors reject requests.

Demonstrates gateway integration, not guaranteed prevention of all attacks.

#security-guardrails#multilanguage-sdk
8564 evidence links
Inspect details
latitude-llm repository icon by latitude-dev

latitude-dev

latitude-llm

4,655
Evaluation & ObservabilityMITTypeScript

Latitude includes an optional Jev preclassifier for conversation checks and their selection records.

What Jev does here

Judges which checks apply and can add checks when thresholds and rate limits permit.

Records models, thresholds, latency and selection reasons alongside the baseline.

#evaluation-benchmarks#voice-conversation
3924 evidence links
Inspect details
3,528
Context GC & FilterMITTypeScript

Prunes old tool calls and outputs for Claude Code while retaining surviving text verbatim.

What Jev does here

Separately judges whether a tool call and its full output are still needed; code keeps, truncates or drops them.

Avoids rewriting paths, commands and errors into a new summary.

#context-compaction#coding-agents
1853 evidence links
Inspect details
ax repository icon by ax-llm

ax-llm

ax

2,926
SDK & IntegrationsApache-2.0TypeScript

Ax provides a TypeSafe integration for boolean or finite-class signatures and native Jev answers.

What Jev does here

Maps supported signatures to Jev questions or sends native System One requests.

Reuses structured signatures and Jev probabilities within Ax workflows.

#multilanguage-sdk#typed-decisions
1953 evidence links
Inspect details
1,287
MCP & IntegrationsMITTypeScript

An optional Jev provider in Vellum Assistant sends conversation state and explicit questions to TypeSafe.

What Jev does here

Submits state and question bundles to System One and returns structured answers to the Assistant.

Adds choices, probabilities, and scoring to an existing assistant.

#mcp-integrations#typed-decisions
1862 evidence links
Inspect details
1,275
Browser & OS ActionApache-2.0Rust

An optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.

What Jev does here

Jev selects a target and action and estimates presence and risk; local policy decides whether to execute.

Keeps the full UI tree out of the main Agent context while exposing the selected action.

#desktop-os#typed-decisions
862 evidence links
Inspect details
celesto repository icon by CelestoAI

CelestoAI

celesto

943
Codebase & Graph PathfindingApache-2.0TypeScript

A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings.

What Jev does here

Judges whether a finding was introduced by the change, is supported and merits a fix.

Shows execution records and reviewer judgments together.

#coding-agents#evaluation-benchmarks
753 evidence links
Inspect details
jev-trader repository icon by jarrodwatts

jarrodwatts

jev-trader

936
Domain & Vertical ToolsMITTypeScript

A market-making experiment on Kuru’s MON-USDC book on Monad, with optional per-block Jev buy/sell decisions.

What Jev does here

In Jev mode, order-book judgments feed code that simulates fills or submits configured post-only limit orders.

Defaults to a mock model and dry-runs without a private key; simulated results do not establish profitability.

#finance-quant#typed-decisions
1774 evidence links
Inspect details

17 Architecture Categories

Explore dedicated category landing pages for architecture patterns and case studies:

SDK & Decision Frameworks

Official & community SDKs, decision primitives, and Agent execution frameworks.

59 repos

High-Frequency & Simulation

Low-latency game AI, real-time simulation, and high-frequency branch evaluation.

29 repos

Evaluation & Observability

Evaluation harnesses, latency profiling, tracing, and telemetry for Jev decisions.

29 repos

Browser & OS Action

Browser automation and desktop OS control with bounded action candidate selection.

26 repos

Routing & Cost Optimization

Complexity-based request routing to tier generative models and optimize token spend.

26 repos

Security & Guardrails

Real-time safety guardrails, prompt injection detection, and moderation gates.

23 repos

Domain & Vertical Tools

Domain-specific decision engines for finance, legal, e-commerce, and vertical ops.

22 repos

Context GC & Filter

Context compaction, tool output pruning, and memory garbage collection.

20 repos

MCP & Integrations

Model Context Protocol (MCP) servers and third-party connector integrations.

18 repos

CLI & Pipelines

CLI utilities, Git gates, CI/CD pipeline checks, and DevOps automations.

18 repos

Data & Search

Search intent classification, query routing, vector re-ranking, and ETL triage.

17 repos

Decision Tools

Standalone decision helpers, schema validators, probability decoders, and utilities.

12 repos

Codebase & Graph Pathfinding

AST traversal, code graph dependency analysis, automated PR review, and pathfinding.

11 repos

Creative Tools

UI layout composition, audio/music pipelines, and creative workflow parameter triage.

11 repos

SDK & Integrations

Third-party framework adapters for LangChain, LlamaIndex, and enterprise stacks.

6 repos

Voice & Conversation

Voice turn-taking, interruption detection, and real-time dialogue routing.

4 repos

Classification & Taxonomy

Hierarchical taxonomy tagging, document categorization, and ontology mapping.

2 repos

Frequently Asked Questions (FAQ)

What is the Awesome Jev Projects Radar?

The Awesome Jev Projects Radar is a developer-centric registry dedicated to TypeSafe Jev and System-1 Agent architectures. Beyond static repo links, it highlights the exact decision point in each codebase where Jev is invoked (Choice, Score, or Noul) and documents the architectural latency/cost gains.

Why delegate bounded decisions to Jev instead of general LLMs?

Generative LLMs excel at creative synthesis and dialogue, but are prone to latency and hallucination when making discrete tool dispatches, safety gates, or routing decisions. Jev evaluates bounded choices in a single forward pass within 200-400ms at minimal token expense.

How are projects vetted and verified for genuine Jev integration?

Every catalog entry undergoes fixed-commit source code review. The radar links directly to public repository files and documentation proving active Jev integration rather than unverified claims.

Why are project detail subpages configured with noindex?

In alignment with technical SEO best practices, the central radar and 17 dedicated category landing pages are fully indexed with rich metadata, while individual repo inspection cards are marked noindex to consolidate crawl equity and prevent thin-content sprawl.