Devika AI

Devika AI

Devika AI is an open-source, self-hosted AI software engineer that understands high-level instructions, breaks them into steps, researches information, and generates code using models like Claude 3, GPT-4, GPT-3.5, and local LLMs via Ollama.

Devika AI is ai agents software teams evaluate for ai agents. Use this page to review pricing, integration signals, and the best alternatives before you commit.

Freemium Enterprise
One of 617 tools in AI Agents
Added 10 months ago
Data reviewed Jul 16, 2026

Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.

Review official source →

Quick Overview

Best for: AI Agents

What it does

AI Agents software for decision-makers comparing workflow fit and alternatives.

Best fit

AI Agents

Pricing snapshot

Freemium from Free (open source)

Next step

Compare Devika AI with similar tools before you shortlist it.

Compare this tool before you shortlist it

Review alternatives, pricing posture, and workflow fit side by side.

Devika AI is an open-source AI software engineer designed to assist with software development by interpreting high-level human instructions, decomposing them into actionable steps, researching required information, and generating code. It targets developers and teams who want a project-oriented assistant that can plan, reason, and produce code in multiple programming languages. The system supports multiple language models (Claude 3, GPT-4, GPT-3.5 and local LLMs via Ollama) and provides a web-based chat interface, project management features, and modules for browsing, code writing, and state tracking.

Open-source AI software engineer that understands instructions, researches, and generates code.

Own this listing?

Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.

Claim this listing for $29

Key Features

AI Planning and Reasoning

Breaks down high-level instructions into actionable steps and uses a planning and reasoning engine to decide how to tackle tasks.

Multi-Language Model Support

Supports Claude 3, GPT-4, GPT-3.5 and local LLMs via Ollama; Claude 3 family is recommended for best performance.

Contextual Keyword Extraction

Extracts relevant keywords from context to focus research and information-gathering efforts.

Web Browsing and Information Gathering

Contains a browser interaction module to search and scrape web content to gather up-to-date information for tasks.

Code Generation in Multiple Languages

Generates code snippets and project files in various programming languages based on task objectives.

Dynamic Agent State Tracking and Visualization

Tracks the agent's state during interactions to maintain coherent, context-aware conversations and workflows.

Natural Language Chat Interface

Provides a web-based chat UI for natural language interaction, project creation, and monitoring agent progress.

Project-Based Organization

Organizes work into projects with directories for repositories, logs, PDFs, screenshots, and other artifacts.

Extensible Architecture

Designed to be extensible, allowing integration of new features and enhancements by contributors.

Pricing

Free Tier Available

Devika AI is open source and available for free; users self-host the software by cloning the repository.

Open Source

Free (open source)
  • Self-hosted deployment
  • Supports multiple LLMs (Claude 3, GPT-4, GPT-3.5, Ollama local models)

Use Cases

Create new software projects

Start a project in the web UI, choose language and model, provide a high-level objective, and have Devika decompose and generate initial code and project structure.

Automated research and information gathering

Use Devika's web browsing and research module to collect up-to-date information needed for implementing features or fixing bugs.

Code writing and prototyping

Generate code snippets and prototypes across multiple languages to accelerate development tasks.

Iterative development and refinement

Monitor progress, review generated code, and provide feedback to refine outputs and iterate on features or bug fixes.

Developer assistance for all skill levels

Assist beginners with guidance and help experienced developers by automating planning, research, and coding tasks.

Integrations

Claude / Anthropic

Supports Anthropic API keys (CLAUDE) to use Claude 3 models.

OpenAI (GPT-4 / GPT-3.5)

Supports OpenAI API keys to use GPT-4 and GPT-3.5 models.

Ollama (Local LLMs)

Supports local LLMs via Ollama for on-device/private model usage.

Search APIs (Google / Bing / DDG)

Configurable web search methods with fields for Bing and Google search API keys and Google Search Engine ID.

Playwright

Uses Playwright for browser automation and browser-interaction capabilities (requires playwright install).

Git / GitHub

Clones and operates on Git repositories as part of project workflows (repository folder configured in settings).

Benefits

Accelerates software development by automating planning, research, and code generation.
Flexible multi-model support (Claude 3, GPT-4, GPT-3.5, local LLMs via Ollama) for varied performance and privacy needs.
Project-based organization and state tracking improves collaboration and continuity across development tasks.

Limitations

Early development stage: the project may contain unimplemented or broken features as noted on the project page.
Requires configuration of third-party API keys (Anthropic, OpenAI, Google/Bing) and local prerequisites (Ollama, Bun, Playwright) to enable full functionality.
Self-hosted setup and runtime environment are required; not provided as a managed cloud service on the referenced page.

Frequently Asked Questions

What is Devika AI?
Devika AI is an advanced software engineering assistant developed by Stition.ai that understands high-level instructions, conducts research, and generates code to accomplish software development tasks.
How does Devika AI work?
Devika AI uses state-of-the-art language models and a planning and reasoning engine to analyze user input, break down tasks into steps, conduct research (via web browsing), and generate code in multiple programming languages.
Is Devika AI suitable for all levels of programmers?
Yes. Devika AI is designed to assist programmers of all skill levels, from beginners to experienced developers, helping with tasks from simple bug fixes to complex feature development.
How can I create a new project from scratch using Devika AI?
Install Devika locally, open the web interface, click 'New Project', select language and model, describe your objective, and Devika will break it down and start working; monitor progress and review generated code.
Can I contribute to Devika AI’s development?
Yes. Devika AI is an open-source project and contributions are encouraged; the project is hosted on GitHub.

Getting Started

  1. 1 Step 1: Install prerequisites (Ollama, Bun, Git, Python) on your system.
  2. 2 Step 2: Clone the repository: git clone https://github.com/stitionai/devika.git and cd into the project directory.
  3. 3 Step 3: Install Python dependencies (pip install -r requirements.txt) and Playwright browsers if needed (playwright install --with-deps).
  4. 4 Step 4: Rename sample.config.toml to config.toml and update required configuration values and API keys (SQLite path, directories, search API keys, CLAUDE/OPENAI keys, etc.).
  5. 5 Step 5: Start the Devika server: python devika.py.
  6. 6 Step 6: Install UI dependencies (cd ui/; bun install) and run the UI server (bun run dev).
  7. 7 Step 7: Open the web interface at http://127.0.0.1:3000 and create a new project to begin.

Support

Docs

Installation and usage instructions are available on the project pages (installation and how-to-use sections).

GitHub

Source code, issues, and contribution guidance available at https://github.com/stitionai/devika.

Discord

Community Discord server (join link available on the website) for discussion, questions, and collaboration.

API

Available: No

Compare Devika AI with similar tools

See how it stacks up against alternatives

Related Tools

View all 617 β†’
Free
Offrun

Offrun

Offrun is a Mac workspace for running and monitoring coding agents such as Claude Code, Codex, AGY, and Grok Build side by side. It adds isolated worktrees, peer review, project memory, and on-device dictation while using your existing agent accounts.

AI Agents
Top source
Contact for pricing
Needle2

Needle2

Needle 2 is an open, production-ready 45M-parameter agentic LLM from Cactus designed for tool calling, device control, and structured extraction on extremely small devices; the shipped CQ2-bit binary is ~14 MB and runs in ~28 MB of RAM across Cortex-M, microcontrollers, phones, Raspberry Pi and WebAssembly.

AI Agents
Top source Enterprise-ready
Freemium
The cheapest GPU cloud

The cheapest GPU cloud

Compute Cheap provides low-cost GPU compute for training and inference, offering H100 and H200 SXM GPUs as interruptible or reserved capacity with published per-GPU-hour pricing and a simple request/reserve/run workflow.

AI Agents
Top source
Aclif

Aclif

aclif is an Agent CLI Framework that builds command-line tools for AI agents, providing a unified command grammar and canonical names across multiple SaaS providers to let agents discover, introspect, and run provider operations with consistent safety and auditing.

AI Agents
Top source
Freemium
Jotbus

Jotbus

Jotbus is an encrypted shared scratchpad for coding agents. Developers use it to pass notes and files, hand off work, and request reviews across agents and machines without copying context between terminals.

AI Agents
Top source
Free
Oodle.ai

Oodle.ai

Oodle Agent Observability provides agent/LLM observability at scale with S3-backed columnar storage, fast search (<1s P99), out-of-the-box AI-powered insights, and flat ingestion-based pricing designed to retain 100% of traces affordably for debugging and optimizing production agents.

AI Agents
Top source
Pod

Pod

Pod (Point of Decision) is an AI-native knowledge sharing platform where agents and humans record, search, and inspect firsthand observations about APIs, products, and services to inform future decisions.

AI Agents
Top source
Contact for pricing
Sentinel

Sentinel

Sentinel is an open-source (MIT) autonomous QA agent that reads a codebase to derive end-to-end business flows and tests them across frontend and backend, combining deterministic repo recon, model-driven planning, Playwright browser automation, and backend assertions.

AI Agents

Premium Alternatives

Paid
Ardent

Ardent

Ardent is a production-ready AI agent desktop app for Apple Silicon Mac that generates custom code to automate and scale business workflows, share reusable "abilities" across teams, and connect to company data sources while running in a secure sandbox.

AI Agents
Paid
Abliterated LLM provider for cyber tasks

Abliterated LLM provider for cyber tasks

Refuseless hosts GLM 5.3 Abliterated models through an OpenAI-compatible API for cybersecurity and coding work. The page states that prompts are not retained and shows integrations with OpenCode and Pi.

AI Agents
Enterprise-ready
Paid
PHNTM ONE

PHNTM ONE

PHNTM One is a private, local-first AI appliance: a hand-built desktop device (Raspberry Pi 5, 8 GB, 10.1β€³ touchscreen) that runs an on-device model (Gemma 3 4B) to provide a voice-capable assistant, memories, document reading, timers, Home Assistant integration and offline knowledge β€” sold as a one-time $549 purchase with no subscription and zero telemetry by default.

AI Agents
Paid
AletheionAGI

AletheionAGI

AletheionAGI provides a grounded-memory layer for AI systems that enforces evidence-bound delivery, namespace isolation, and policy authorization so AI readers cannot produce unsupported claims. It's targeted at production-facing use cases like customer support, commerce agents and internal copilots.

AI Agents
Paid
Pact0

Pact0

Pact0 is a marketplace where AI agents perform small paid tasks and build a portable, signed work record; the site also offers reproducible audits of how well an agent can cold-start against a live product and public graded challenges (Pact Trials).

AI Agents
Enterprise-ready
Paid
ClaudeThings

ClaudeThings

ClaudeThings provides a packaged, continuously-updating set of 89 specialized agents, 103 pre-built skills, and 181 slash commands that act as an AI engineering and marketing team for Claude Code β€” delivered as a private GitHub repo and installed with a single npx command. It adapts to any stack via a CLAUDE.md project manifest and is sold as a one-time purchase with lifetime updates.

AI Agents
Paid
eesel AI

eesel AI

eesel AI provides autonomous agents for customer service, content creation, and operations that work across a team’s existing apps. Agents can use company knowledge to resolve or draft support replies, escalate complex cases, and handle other workflows.

AI Agents
Enterprise-ready
Paid
REP AI

REP AI

REP AI is an AI commerce platform for ecommerce brands that engages shoppers, answers sales and support questions, and analyzes conversations across website, email, and social channels. It offers separate sales and support agents, plus a combined concierge plan.

AI Agents

Explore Related Categories

Explore by Outcome