Projects tagged with “ai-agents”
Browse Jev GitHub projects tagged with ai-agents. Filter, sort and explore their source repositories.
- 1cuaScale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
trycua/cua · Rust
32,4182,442ai-agentsapplecomputer-usecomputer-use-agentcontainerizationcua - Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
ComposioHQ/composio · TypeScript
31,0924,950agentic-aiai-agentsdeveloper-toolsfunction-calling - 🚀 The fast, Pythonic way to build MCP servers and clients.
PrefectHQ/fastmcp · Python
28,5602,611ai-agentsfastmcpllmsmcpmcp-clientsmcp-servermcp-tools - Browser Use × Jev Ultrafast — high-speed browser automation powered by TypeSafe Jev. i. am. speed.
browser-use/jev-ultrafast · Python
24,5311,889browserultrafastai-agents - One AI trade decision every Monad block — Jev on Kuru MON-USDC.
jarrodwatts/jev-trader · TypeScript
3,140600tradingai-agents - 16skillsAgent skills for building with TypeSafe's System One API.
typesafe-ai/skills
2,902187ai-agentsskillsofficial - Follow your curiosity. Build across disciplines. Open-source software and hardware for polymaths in the making.
autonomous-ai/openharness · TypeScript
1,4951453d-modelingagent-frameworkagent-harnessai-agentscadclaude-codecodex - Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click (macOS).
awlevin/typesafe-computer-use · Python
1,306124ai-agentscomputer-usebrowser - 5–10x faster browser operations: Jev clicks, Codex thinks and verifies.
wy-coliney/jev-browser-use · JavaScript
1,21434browserai-agents - 32foremanSoftware Factory Foreman based on TypeSafe Jev model.
thruwire/foreman · Python
82770ai-agentsfactory - A monorepo of Pi Coding Agent extensions
narumiruna/pi-extensions · TypeScript
785158ai-agentscodexcodex-clicoding-agentsnodejsnpm-packagepi - Staged code-review workflow and local dashboard built with TypeSafe Jev.
devagrawal09/jev-review · TypeScript
70346ai-agentscode-review - Route to the cheapest model in Claude Code for your task using jev-router.
gargpratyush/jev-router · JavaScript
668102routerai-agents - Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.
AbdelStark/awesome-typesafe-jev · HTML
618161agent-skillsai-agentsawesomeawesome-jevawesome-listcurated-list - 1207 public resources for Jev, TypeSafe AI's System One decision model, indexed by decision pattern. Source citations, dated link checks and scheduled call-site text checks; runtime and performance are not independently tested here. EN/中文, JSON schema and platform compatibility.
kydlikebtc/awesome-jev · Python
60234agent-toolsai-agentsawesomeawesome-listcalibrationcatalogclassification - A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.
fhshaik/typesafe-mario · Python
46364ai-agentsgame - Browser use using TypeSafe's Jev model.
jkudish/jev-browser · JavaScript
37236browserai-agents - MCP connector giving AI agents direct access to TypeSafe AI's Jev model.
itsmostafa/system-one-connector · Go
36142mcpai-agents - 73skillboxSelf-hosted, versioned skills library for AI agents — MCP, scoped clients, optional Jev recommendations.
kitze/skillbox · TypeScript
28228ai-agentsskillsmcp - Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.
0xNatoshi/jev-codex-router · JavaScript
27548ai-agentsrouter - Jev DSH 决策引擎|面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness,通过 iPolloWork 支持 OpenCode、Codex Harness。
Devin-AXIS/jev-dsh-decision · JavaScript
27484agent-harnessai-agentsapollo-plugincodexcodex-harness-plugincodex-plugindecision-engine - Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
NiazMorshed2007/jev-review · TypeScript
25325mcpcode-reviewai-agents - A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.
agent-labs-dev/fastbrowse · Rust
23029browserai-agents - Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev or Decision api like luna as a System One decision layer for agent selection, supervision, corrections, and approvals.
luobosibing2/dsh-jev-plugin · JavaScript
21421agent-harnessai-agentscordisdecisions-apideepseek-harnessdshdsh-jev - Jev-powered Instagram, TikTok, and LinkedIn research: typed routing, real browser evidence, streamed post cards, video capture, and cited socai reports.
socai-io/jev-social · JavaScript
21343agent-skillsai-agentsbrowser-agentbrowser-automationcomputer-usedecision-modeldeep-research - A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and Noul with calibrated probabilities.
kraayenjon/awesome-jev
20748ai-agentsapiautomationawesome - Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop
DevMortimer/pi-warden · TypeScript
19332ai-agents - System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
ThinkFlowLab/system1-agents · Python
18426ai-agentsbrowser-agentbrowser-automationclaude-code-plugincomputer-usecuadecision-model - 99pi-jevTypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers
y0usaf/pi-jev · TypeScript
16516ai-agents - Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
aaddrick/building-with-typesafe-jev · Python
15612agent-skillsai-agentscalibrationclassificationclaude-codeclaude-code-plugin - 102jev-guardAuto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.
leepokai/jev-guard · JavaScript
15325javascriptai-agentsclaude-codecodex - 105awesome-jevA source-backed Jev / System One knowledge map: projects, papers, evaluations, robotics, and social discovery.
Promethe-us/awesome-jev
14913ai-agentsai-researchawesome-listdecision-modelembodied-aillm-resourcesmachine-learning - 106quicksilverClaude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.
UditAkhourii/quicksilver · JavaScript
14212ai-agentsclaudeclaude-codedeveloper-toolsllmskillstokens - 107skillrankerRust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.
Dicklesworthstone/skillranker · Rust
14212ai-agentsskills - 111RSI-JevTyped-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.
Shanghua-Gao/RSI-Jev · HTML
13712ai-agentsautonomous-researchdecision-modelllmrecursive-self-improvementtyped-decisions - 117jev-useSay it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model
savka777/jev-use · Swift
13219accessibilityai-agentsbrowser-usecomputer-useharnessmacos - 122agent-routerCLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr
nidhi-singh02/agent-router · TypeScript
12316ai-agentsclaude-codeclicodexcodingdeveloper-tools - 123jevalsAgent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.
openlayer-ai/jevals · Python
12013ai-agentsevaluationguardrailsllmllm-evaluationragas - 128winnowA calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.
GhalebDweikat/winnow · Python
11512ai-agents
1–50 of 368