Build a research brief you can actually check
Turn three source passages into a claim ledger, a restrained recommendation and a one-page brief. Includes a complete teaching packet and reusable prompts.
Work through the example ↗The practical AI decision desk
Useful work.
Clear evidence.
Choose a task, check the evidence and measure the result. Worked guides, an editable cost model and a tool shortlist help you make the next decision.
Start with the job
What are you working on?
A good tool earns its place in your workflow.
Build somethingApps, code & developmentFind an answerResearch & source checkingMake it visualImages, UI & presentationsGet time backWorkflows & integrations
No signup. Save locally. Compare before you commit.
● 832 tools in the directory4 worked guides & templatesLatest source record 13 Oct 2026Our publishing method ↗
Start here / Learn a useful method
Go from a question to a checked result.
Original teaching examples, complete exercises and reusable templates.
Compare the cost of finished work, not the subscription
Build an editable monthly cost model with retries, review time and setup. Follow a hypothetical USD example and calculate a useful break-even point.
Work through the example ↗Run a small AI coding pilot with a reviewable result
Use a two-tool compare action as a bounded coding exercise. Includes acceptance criteria, a reference function, runnable tests and a diff-review checklist.
Work through the example ↗Make a small automation safe to retry
Design one draft per request version, recognize duplicate deliveries and stop conflicting inputs. Includes runnable sample logic and a production handoff checklist.
Work through the example ↗Your assumptions / Your decision
A cheap plan can make expensive work.
Compare recurring charges, review time and setup. Record your acceptance task, source checks and corrections in a worksheet you can download.
EXAMPLE: $220 vs $85 / MONTHOpen the decision lab Fictional inputs. Runs in your browser.
Find candidates. Then run your own trial.
These source briefs are unreviewed discovery records, not tested recommendations. Search, save candidates and verify the original source.
228 tools
imaginAIryBuild & code
Generates images and videos using Python. Open-source contributions possible via GitHub. Requires further validation for production use.
free claude codeBuild & code
Access multiple AI harnesses for free with browser support and high token availability. Suitable for terminal, IDE, and app integration.
Apollo 11 Guidance Computer CodeBuild & code
Source code for Apollo 11 Guidance Computer. Supports lunar and command module simulations.
AnyPS5Build & code
Tool automates porting of PS5 executables to Linux and Windows systems. Simplifies cross-platform compatibility for developers.
andrej-karpathy-skillsBuild & code
Enhances Claude's code performance using insights from Karpathy on LLM coding errors.
pytorchBuild & code
Python library for tensor computation and dynamic neural networks. Supports strong GPU acceleration for efficient training.
flutterBuild & code
Cross-platform framework for mobile app development. Supports building natively compiled applications for mobile, web, and desktop from a single codebase.
context-modeBuild & code
Optimizes context windows for AI coding agents. Reduces tool output drastically, maintains session memory, routes across multiple platforms.
PocketFlowBuild & code
Codebase documentation tool converting repositories into tutorials. Community contributions encouraged for development enhancement.
z80aiBuild & code
Z80-μLM enables training and exporting conversational models for vintage Z80 systems, targeting niche use cases in retro computing.
open-code-reviewBuild & code
Code review tool uses hybrid architecture for deterministic pipelines and LLM Agent, supports multi-language ruleset and line-level comments.
SwiftUI-Agent-SkillBuild & code
Integrates SwiftUI with Claude Code, Codex, and AI tools. Facilitates development of agent skills using SwiftUI framework.
litellmBuild & code
Rust-based AI gateway with Python SDK for multiple LLM APIs. Features cost tracking and load balancing.
cmuxBuild & code
Open source terminal for macOS with vertical tabs, notifications, focused on AI coding agents.
raddebuggerBuild & code
Graphical debugger for user-mode, multi-process applications. Focuses on efficiency and visual capabilities.
agent-skillsBuild & code
Library for engineering skills tailored for AI coding agents. Focuses on enhancing AI coding capability and integration.
i-have-adhdBuild & code
Skill for concise coding responses, reducing unnecessary output for ADHD users.
OpenVulnBuild & code
Detect bugs in code repositories using GLM technology. Focuses on identifying vulnerabilities in applications.
gstackBuild & code
Toolset for software development and team roles. Integrates 23 tools for various management and engineering tasks.
pstackBuild & code
Agent workflows with Cursor primitives. Translates pstack for various AI platforms. Multiple code base versions available.
ponytailBuild & code
Generates code suggestions based on minimal effort concept. Less focus on best practices or performance optimizations.
t3codeBuild & code
Code generation tool using T3 stack principles. Target audience includes developers seeking streamlined integration and efficiency.
Effect-TSBuild & code
TypeScript library for building applications. Supports functional programming paradigms. Focuses on composability and type safety.
ECCBuild & code
Optimizes performance in coding tasks using skills, instincts, memory, and security. Focuses on research-driven development.
No tools match yet.
Try another search or reset the filters to explore the directory.
Follow the evidence
Each source brief links to its origin. Use the research guide to turn claims into a checked evidence ledger.
Choose on your terms
Compare source descriptions side by side, then use the decision lab to model costs and record a trial.
Try before you trust
Set an acceptance condition before trying a tool. Record review time, errors and the result before adopting it.