Jiva는 맨끝과 구름을 위한 자율적인 AI 대리인입니다. OpenAI 호환 모델 공급자와 함께 작동하고 두 개의 실행 모드를 지원 - 범용 두 시약 시스템 (Manager + Worker) 복잡한 작업을 위해, 및 소프트웨어 공학에 대한 LSP 통합과 코드 최적화 단일 루프 엔진.

데모

---

설치

설정 마법사는 공급자 선택 메뉴로 엽니다. 공급자를 선택하고 Jiva 자동 채우기 엔드 포인트, 모델 이름 및 도구 형식을 선택하십시오. API 키 만 공급하십시오. 지원 제공 업체: Krutrim, Groq, Sarvam, OpenAI, OpenAI 호환 엔드포인트.

설정 후, 실행 jiva benchmark 을 확인하기 위해 선택된 모델과 구성 작업에 최적으로 코드 모드에서. baseline (taskstore) Suite - 구성에 대한 코딩 작업의 결정적인 세트; 건강한 설정은 모두 전달합니다. 튜닝 및 기능 비교에 대한 벤치 마크를 참조하십시오.

개발 설치

---

빠른 시작

REPL 명령

Jiva

Jiva is an autonomous AI agent for the terminal and cloud. It works with any OpenAI-compatible model provider and supports two execution modes — a general-purpose two-agent system (Manager + Worker) for complex tasks, and a code-optimized single-loop engine with LSP integration for software engineering.

Demo

---

Installation

npm install -g jiva-core
jiva setup

# Verify your model + config can do code mode well:
jiva benchmark

The setup wizard opens with a provider selection menu. Choose your provider and Jiva auto-fills the endpoint, model name, and tool format — you only supply your API key. Supported providers: Krutrim, Groq, Sarvam, OpenAI, and any OpenAI-compatible endpoint.

After setup, run jiva benchmark to confirm your chosen model and configuration work optimally in code mode. It runs the baseline (taskstore) suite — a deterministic set of coding tasks — against your config; a healthy setup passes all of them. See Benchmarking for tuning and capability comparison.

Development install

git clone https://github.com/KarmaloopAI/Jiva.git
cd Jiva
npm install && npm run build && npm link
jiva setup

---

Quick Start

# General-purpose interactive session
jiva chat

# Code mode — optimized for software engineering tasks
jiva chat --code

# Code mode with plan-then-approve flow
jiva chat --code --plan

# Single prompt
jiva run "What changed in the last 5 commits?"

# Single prompt in code mode
jiva run "Add error handling to the database module" --code

REPL commands

---

Execution Modes

General mode (default)

A two-agent pipeline designed for complex, multi-step tasks:

User Request
    ↓
Manager Agent    — plans, decomposes, and synthesizes
    ↓
Worker Agent     — executes subtasks with MCP tools
    ↓
Response

The Worker has access to any configured MCP server (filesystem, browser automation, shell commands, etc.). The Manager synthesizes results from all subtasks into a final coherent response. Simple conversational messages are answered directly without executing subtasks.

Code mode (--code)

A single streaming loop optimized for coding tasks: