Alternatives to Bedrock Engineer

Open-source coding agent that edits files and runs bash commands in your IDE, terminal, or desktop app.

Cursor is an AI coding agent that plans, builds and ships features from your editor, CLI, Slack, GitHub and iOS.

Amp's $0 Hobby tier: the full agentic coding agent, with you supplying the models and the compute.

Open-source terminal coding agent that reads your repo, edits files, runs commands, and uses the model you choose.

Open-source autonomous AI coding agent for VS Code and JetBrains that plans, executes, and deploys tasks with step-by-step reasoning.

OpenAI Codex is a cloud coding agent that runs parallel software engineering tasks in isolated sandboxes

Open-source AI coding agent you drive from the terminal, desktop app, or IDE, with free models included.

Kilo is an open-source AI coding agent delivering 500+ models at exact provider rates with zero inference markup.

Emdash is an open-source agentic development environment for running parallel CLI coding agents in isolated Git worktrees.

Openclaude is an open-source terminal coding agent CLI you install with npm and point at any model backend — OpenAI, Gemini, or local Ollama.

Godcoder is a free, open-source desktop coding agent that builds and optimizes its own harness while your code stays local.

Parallel coding agents in isolated git worktrees, from one open-source desktop IDE

Kiro Crew is an open-source agentic coding workspace with persistent memory, scheduled jobs, and multi-agent crews.

Open-source, local-first orchestrator that runs parallel AI coding agents in isolated git worktrees, from a one-line idea to a merged pull request.

Pane is a free, open-source agent manager that runs Claude Code, Codex, Cursor and any CLI coding agent in parallel git worktrees.

Open-source AI coding agent orchestration that turns tickets, crons, and webhooks into merged pull requests on your own Kubernetes cluster.

TalkCody is a free, open-source AI coding agent with four-level parallel execution and any-model support.

WeSight is an open-source desktop workspace that runs Claude Code, Codex and other CLI coding agents side by side.

Self-hosted, open-source agentic dev IDE that spawns, coordinates, and tracks fleets of coding agents partitioned by file path on your own tailnet.

Open-source, MIT-licensed terminal workspace for running and orchestrating multiple AI coding agents in parallel.

Anthropic's agentic coding assistant that reads your repo, edits multiple files, runs tests and keeps going until the ticket is closed.

OpenHands runs autonomous coding agents that review PRs, fix CI failures, and open pull requests from GitHub, Slack, Jira, or Linear.

Kimi K2.6: open-weight long-horizon coding with 12-hour autonomous runs and agent swarms

Hermes Agent: a self-hosted open-source AI agent with persistent memory that builds reusable skills across 20+ chat platforms.

Localforge is a free, MIT-licensed desktop coding agent GUI that runs autonomous multi-file code edits in your own repo with any LLM.

Devstral 2 and Mistral Vibe CLI bring open-weight agentic coding to your terminal at $0.40/$2.00 per million tokens

Replicas runs Claude Code, Codex, Cursor, and OpenCode coding agents in isolated cloud VMs and hands back pull requests.

Open-source long-running AI agent loop that works through a task list in Docker Sandboxes and commits the results.

Open-source framework that generates hundreds to thousands of SWE-agent training tasks from any GitHub repository.

Terminal coding agent with hash-anchored edits and the IDE wired straight into your shell