Factory provides software-development agents and automations spanning planning, implementation, validation, release, monitoring, and documentation.
Developer tools
47 companies
Developer tools listings
E2B supplies isolated cloud sandboxes where AI agents can execute code, use computers, access files, and run long-lived tasks.
CodeRabbit reviews pull requests and code from IDE, CLI, and repository workflows using contextual AI analysis and automated fixes.
Morph provides inference and specialized models for coding agents, including high-speed code generation and edit application.
Browserbase provides managed browsers, web-data APIs, agent runtimes, identity, model access, and observability for web-using agents.
Ampere deploys managed OpenClaw agents in roughly a minute with hosted infrastructure, application connections, and starter model credits.
Lovable turns product descriptions into working web applications with editable code, backend integrations, collaboration, and deployment.
Bolt builds and runs production-oriented web applications in the browser from natural-language instructions, including databases and deployment.
Devin is an autonomous software-engineering agent for migrations, refactors, issue resolution, documentation, testing, and scheduled engineering work.
Cline is an open-source coding agent that understands repositories, edits files, runs commands, uses browsers, and supports many model providers.
Dify provides visual agentic workflows, retrieval, model management, observability, evaluations, and application deployment.
Cuttlekit generates interactive interface components from conversation and lets users refine working forms, controls, and layouts in place.
Syllabi builds agentic chat systems that combine RAG knowledge bases, custom tools, web widgets, standalone apps, and channel deployment.
Infrence exposes deep web research through one API with citations, structured output, depth controls, budgets, time limits, and webhooks.
Moshi is a native mobile control surface for Claude Code, Codex, Cursor, OpenCode, Gemini, tmux, shells, and long-running coding sessions.
Codex with ChatGPT connects the official ChatGPT web interface to a local Codex workspace through a read-only MCP bridge for planning and review.
My Free Code runs a local gateway that translates agent protocols, routes models across hosted or local providers, handles fallbacks, and launches multiple coding-agent clients.
Pentest Harness is a self-hosted multi-model agent workspace for authorized penetration tests, bug bounties, security labs, and CTF exercises with local sessions and owner-controlled credentials.
Reverify is a CLI and MCP toolkit that checks AI claims against executable ground truth, records evidence, and preserves verified context across agent-session resets.
Reef captures agent usage, feedback, and evaluation, then versions improvements to model weights or agent harnesses through governed recipes and reviewable releases.
OKF Agent Memory stores agent knowledge as auditable Markdown, retrieves it through local BM25 search, tracks provenance and trust, and exposes the corpus through a zero-dependency Go CLI and MCP server.
Client-side workbench that converts Claude Code, Codex, and OTLP traces into searchable timelines, metrics, heuristic diagnostics, comparisons, and privacy-conscious exports; recorded commands are not executed.
Local project-delivery platform that connects goals, tasks, dependencies, context, checkpoints, and evidence through CLI and MCP across sessions and agents.
Agent skill that drives EasyEDA Pro through MCP from concept to schematic, sourcing, layout, routing, independent Gerber verification, and staged purchase; checkout and payment remain manual.
Desktop and CLI workspace combining Claude Code, Codex, Devin, Grok, Gemini, or API providers with chats, files, terminal, browser, worktrees, plans, child tasks, and recurring heartbeats.
Self-hosted Cloudflare Worker that gives agents REST and MCP inboxes, verification-code waits, threading, attachments, sending, replies, signed webhooks, search, and retention controls.
Local gateway that masks credentials, PII, network data, and custom terms before AI API or browser calls, then restores placeholders in streaming responses.
Self-hosted Codex SDK controller that turns selected GitHub issues or PR findings into frozen tests, bounded repairs, independent Docker verification, and optional draft PRs without merge or deployment.
Dependency-free CLI that strictly parses agent tool-call transcripts, detects replay divergence and permission overreach, and emits deterministic reports with tamper-evident hashes.
Self-hosted control plane for immutable skill revisions, scoped clients, grants, GitHub imports, MCP, backups, usage, and recommendations without executing skill code.
Open software-factory environment that connects persistent coding agents, repository workspaces, issue intake, triage, planning, implementation, and review with human gates.
Desktop agent that connects to Unreal Editor through more than 100 tools and 25 skills for levels, Blueprints, materials, assets, C++, animation, UMG, Sequencer, and in-engine verification.
Async-first Go agent harness with append-only sessions, deduplicated inputs, durable operations and steering while tools run in background.
Stable Astro CMS with built-in admin, MCP/OAuth, API/CLI, bundled agent skills and permissioned sandboxed plugins.
Runtime for agent fleets in kernel-isolated sandboxes with declarative policy, credential injection, observability and runtime checks.
Local desktop app installs, updates and repairs ten AI CLIs while managing providers, skills, MCP servers, prompts and sessions.
Local 0.6B decision model returns calibrated distributions for boolean, choice and score questions without text decoding.
Agent acceptance testing turns outcomes into checks, operates real web/CLI/native surfaces and publishes screenshots, recordings and logs.
Self-hosted harness joins Claude Code, Codex and Pi into persistent named teams with durable roles, queues, direct messages, TUI, MCP and tmux workspaces.
Operational-assurance auditing for deployed agents, with self-hosted inspections and paid suites covering purpose, authority, workflows, evidence and governance.
Cross-platform agent development environment runs Codex, Claude, OpenCode and Pi side by side in isolated worktrees with mobile monitoring and diff review.
Agent memory layer with retain, recall and reflect, mental models and knowledge pages; self-hosted, embedded or managed.
Alibaba hybrid deterministic-plus-agent CLI reviews diffs/files with line comments, built-in rules, codebase search and parallel bundles.
CodeGraph builds a locally synchronized graph of symbols, calls, imports and routes so coding agents can inspect dependencies and change impact through MCP.
ai-memory gives coding agents shared, self-hosted memory and typed handoffs, with Git-backed Markdown as the durable source and a rebuildable retrieval index.
Magnitude runs open-weight models locally through a desktop app, headless CLI and compatible inference APIs, compiling and tuning kernels for the machine's hardware.
Operator Memory gives coding agents durable Markdown specifications, decisions, standards and indexes across private project, shared project and user-global partitions.