iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Install Jac’s self-contained command-line binary, verify it with jac --version, then configure an AI model backend before running an AI-backed program. For a first agent, save a .jac file that exposes an ordinary Jac function as an LLM tool and run it with jac run first_agent.jac. Installing Jac gives you the language and CLI; it does not by itself supply hosted-model credentials or set up a local inference service.
What do you need to run a Jac AI agent?
You need the Jac command-line tool, the optional byLLM dependencies resolved for your project, and access to a model. Model access means either credentials for a hosted provider or a local inference setup such as Ollama. The official Jac installation page describes its recommended installer as downloading a self-contained native binary; it says you do not need system Python, pip, or uv to install or run that binary.
In this guide, an “agent” is an LLM-backed Jac function that can use tools: ordinary Jac functions made available to the model. The model can decide to call a tool, supply its arguments, and use the function’s result when composing its answer. That is different from a plain model-backed function that only generates a response from its input.
- A terminal in which to run the Jac installer and commands.
- A project directory for the sample
.jacfile. - A model backend: a provider API key, or a configured local option.
- Network access for installation and, depending on your choices, dependency resolution or model downloads.
The official documentation is rolling and does not provide a stable publication date in the material cited here. Commands and model examples below reflect the official Jaseci Labs guides accessed October 26, 2026; check those guides and provider instructions if a command, model name, or provider requirement changes.
#1 Best Overall
- Powerful Turbo Fan:CAGIWIRU Electric Air Duster have reached speed up to 130000RPM,Can efficient remove dust and debris.With LED light and Three Adjustable Speed to meet with different cleaning tasks.
- With Attached USB C Fasting Charging cable.Charing 3 hours,Enjoy up to 240 minutes of use on the lowest setting, For third speed can use for 25mins.with four charging options to meet with your needs.
- Wide Application: attached 5 different nozzles,making it suitable for a variety of scenes, such as car,pet, pc, keyboards, and other electronic devices. It also serves for office and home clean duster.
- Handy Design & Portable:Cordless air duster electric nozzle is Light weight and small size, design and comfortable to hold and space saving, convenient to carry around. You can put it in your room or inside the car without taking up space.
- Economical &Reusable: Built durable materials with a long-lasting battery,our CAGIWIRU air duster it's a sustainable alternative to disposable air cans.
How do I install Jac and check that it works?
Use the official shell installer, then check that the jac command is available. The installer page says the command downloads the native binary and places it on your PATH. Jaseci Labs describes the installation as taking under two minutes; that is its estimate, not a guarantee for every connection or machine.
-
Open a terminal and run the installer command documented by Jaseci Labs:
curl -fsSL https://raw.githubusercontent.com/jaseci-labs/jaseci/main/scripts/install.sh | bashThis runs the installer script fetched from the official Jaseci Labs repository. If your environment does not permit piping a downloaded script directly into a shell, follow your organization’s security policy and the current official installation instructions instead.
Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy. -
Ask Jac to report its installed version:
jac --versionA version response confirms that the shell can find the CLI. The installer supports selecting a version with
--version V; consult the current installation page for the exact version-selection invocation before pinning a release. The rolling installer may install a different release over time, so do not assume a version number from an older tutorial. -
Create a small file named
hello.jacin your working directory:with entry { print("Hello from Jac!"); }Run it with either of the equivalent CLI forms:
jac hello.jac jac run hello.jacThis verifies the basic language workflow without involving a model account, provider key, or inference service. The
with entryblock is the program entry point in this small example. You do not need to scaffold a web application just to run a single local file.
If Jac is installed but the shell reports that jac cannot be found, the immediate issue is command discovery rather than model configuration: confirm the installer completed and that the binary’s location is on your PATH, then follow the current installation guide for your shell. If the command runs, but the file reports a syntax or runtime diagnostic, inspect the file and use the CLI diagnostic option described below.
Quick wins for a faster PC:
Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Install optional AI dependencies
The Jac binary includes byLLM capability, but an AI project may still need optional third-party dependencies. From the project directory, resolve those dependencies with:
jac install byllmThis command is distinct from installing the Jac CLI. The CLI is the language tool; jac install byllm prepares the project’s optional AI-related dependencies. In other words, “Jac installed” does not mean every dependency required by a chosen AI setup has already been fetched. The exact additional work depends on whether you choose a hosted provider, Ollama, or the in-process local runtime.
Keep the command in the context of the project you intend to run, and let it finish before trying the AI examples. If dependency resolution fails, check your network and the current Jac instructions; do not assume that installing Python packages manually is the fix, since the documented Jac workflow uses Jac’s own install command.
Choose a model backend: hosted API or local inference
Jac provides the language and AI integration pattern, but a model has to answer the LLM call. You can route requests to a hosted provider using that provider’s API key, or configure local inference. The official tutorial lists provider keys including OPENAI_API_KEY, ANTHROPIC_API_KEY, and GOOGLE_API_KEY. Use the key for the provider and model you actually select, and follow that provider’s current instructions for creating and setting credentials.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsRank #2
- Screen Cleaner is Your Screen’s New Bestfriend! - EVEO is proud to present a screen cleaner that’s perfectly suited for your TV. Meet your new screen cleaner, computer screen cleaner, laptop cleaner, iPad cleaner, Macbook,tv cleaner or any other electronic device. Our screen cleaner spray and wipe along with the included plush microfiber cloth, easily removes dust, fingerprints & other smudges on the screen’s surface. Clean effectively for a streak-free screen
- Gentle on your Screens - Our screen cleaner spray and wipes is compatible to be used even for the most sensitive LCD, LED, CRT, and OLED screens in proper use. Be at ease knowing that this product is compatible with all the major brands: LG, SONY, Samsung, Sharp, iPad, iPhone, Android screens, Kindle, PC monitors - we’ve got you covered! Can be used as LCD screen cleaner, tv cleaner, smart tv screen cleaner, and more
- Premium Super Soft Plush Microfiber Cloth - Included in this efficient screen cleaning kit. This screen cleaner spray and wipe has our signature plush microfiber cloth specially designed to comply with screens and monitors and leave them streak-free. Has been shown to effectively absorbs stubborn stains, zero streaks, and no fiber shedding. Always use this together with our screen cleaner for the best results
- Easy-to-Use Screen Cleaner Kit + microfiber cleaning cloth - The EVEO Screen Cleaning Kit will easily be your new favorite tool when it comes to taking care of the things you love most, quick and easy solution for a streak-free screen. Simply screw on the sprayer gun on the screen cleaner bottle. Spray the cleaning liquid onto the microfiber cloth, then wipe the screen until desired cleanliness & shine is achieved.
- Quality Screen Care Kit Worth Purchasing - Enjoy a convenient Screen Cleaner anytime, anywhere you need it. Your satisfaction is our top priority. We stand behind the quality of our products and that’s why, you shouldn’t be worrying at all. We manufacture the Best Screen Cleaner. and can be used for laptop cleaning kit, laptop screen cleaner, tv screen cleaner for smart tv. MacBook screen cleaner, monitor cleaner or screen cleaner spray for electronic devices with microfiber cleaning cloth
A hosted service avoids installing a local model runtime, but it requires a provider credential and sends model requests through that service. The cited Jac setup material does not establish a price comparison, performance ranking, or universal privacy conclusion among providers, so choose according to your own provider requirements rather than assuming one option is always cheaper or faster. Keep credentials out of source files and do not commit secrets to a shared repository.
Option 1: Use a hosted provider
Set the relevant provider key in the environment used to run Jac. For example, a project using OpenAI’s provider needs the OPENAI_API_KEY variable available to that process; a project using Anthropic or Google needs the corresponding listed variable. The provider’s current documentation is the right place to check how to create a key and set it for your operating system or shell. The key name by itself does not choose a model: make sure the model configuration and credential correspond to the service you intend to call.
Do not paste a real secret into a tutorial file or publish it in a code sample. If Jac reports a missing credential, first verify that the variable is set in the same terminal session or process environment from which you invoke Jac. A key set only in another terminal, editor, or account may not be visible to the running program.
Option 2: Run a local model with Ollama
The Jac guide recommends Ollama as its local inference path. Ollama is installed separately from Jac. After installing it according to its current instructions, pull a model such as gemma3:4b, then configure byLLM to use that model:
Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstall[byllm.model]
default_model = "ollama/gemma3:4b"This route runs inference locally through the Ollama service, so it has a separate runtime requirement: Ollama must be installed and available when your Jac program makes its model call. Pulling a model is also a separate step from installing Jac or resolving byLLM dependencies. The model name shown here is the official tutorial’s example; model choices and instructions can change, so check the current Ollama and Jac guides for the one you intend to use.
Ollama is useful when you want local inference and are comfortable maintaining a separate service and model installation. It is not necessary for the basic Jac hello-world file, nor is it included simply by installing the Jac binary.
Option 3: Use the in-process local runtime
The other local choice in the tutorial is an optional in-process runtime, installed with:
jac install 'byllm[local]'Unlike the Ollama route, the in-process option avoids a separate daemon. Its trade-off is that the first use downloads a model of about 5 GB, according to the official guide. Allow for that download and the local requirements specified by the current runtime instructions. It is an optional route, not an extra package every Jac user needs.
In short: choose a hosted API if using a provider credential and its model service fits your setup; choose Ollama if you want local inference through a separately installed service; choose the in-process extra if you prefer not to run a separate daemon and can accommodate the initial model download. The cited setup material does not provide a cost or speed comparison between these alternatives.
Run a first AI-backed function
Before making a tool-using agent, you can test the simpler pattern: a Jac function whose response is generated by an LLM. The official quickstart’s example is a function that translates text into French, declared with by llm(). A semantic description can explain the function’s purpose to the model:
def translate2french(text: str) -> str by llm();
sem translate2french {
"Translate the supplied text into French."
}
with entry {
translated = translate2french("Good morning");
print(translated);
}Save a version of the example as hello_ai.jac and run:
Rank #3
- 【Large size】：Measuring 800 x 300 mm/ 31. 5×12 inches, which is wider and taller than others. Large mouse pad can perfectly fit your keyboard and mouse of any size, and there is also ample space for peripherals such as phones, tablets, etc.
- 【LED backlight mouse pad】：Blade Hawks RGB mouse pad provides 7 static modes and 7 dynamic modes will give you the options you are looking for. Power-off memory function remembers the last lighting mode you selected. The super glow fiber Chroma will give you a colorful gaming setup that you want.
- 【Anti-slip rubber base】：Made from Natural rubber, this gaming mousepad will firmly grip your desktop, allowing you to enjoy the ultimate precision in the games you are most passionate about. It also comes with a texture that enhances this ability even further.
- 【Smooth and waterproof surface】: Micro-textured cloth surface, for extremely precise mouse control and a smooth movement. When liquid splashes on the gaming mouse pad, it forms water droplets and slides down. Will not delay your work or gameplay.
- 【Plug and play】: This mouse and keyboard pad is powered by USB, plug and play, no driver required. One button control light modes. Press one time to change the lighting mode, press twice to change the brightness, press and hold about 3 seconds turn ON/OFF.
jac run hello_ai.jacThe function name, argument and return types, and semantic description provide context for the generated prompt. This compact example is a useful checkpoint: it confirms that your project can make an LLM call, but it does not demonstrate the model choosing and calling a Jac tool. The official quickstart estimates about 20 minutes for its tutorial; that is the guide’s estimate, not a required duration.
Build a first tool-using AI agent
For a concrete first agent, expose a regular Jac function as a tool and pass it to the LLM-backed function with tools=[...]. The example below gives the model a clock function it can call when a user asks for the current time:
def get_current_time() -> str {
import datetime;
return datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S");
}
def answer(question: str) -> str by llm(
tools=[get_current_time]
);
with entry {
response = answer("What time is it right now?");
print(response);
}-
Save the file as
first_agent.jacin the project directory where you resolved the byLLM dependencies. -
Make sure the chosen model backend is ready. For a hosted option, the relevant provider key must be available to the process. For Ollama, the service and selected model must be set up. For the in-process route, the optional extra and model download must be complete.
-
Run the program:
jac run first_agent.jac -
Read the response. The example asks about the time, so the model can determine that the supplied clock tool is useful, call
get_current_time(), receive its returned string, and use that result in its answer.The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
The important distinction is that get_current_time is an ordinary Jac function, while answer is the LLM-backed function that receives the tool list. The model may select a tool, provide its arguments, and incorporate the returned result. The function is not a hard-coded call inside the body of answer; it is made available to the model through the tools argument. That tool access is what makes this example more agent-like than a function that only asks a model to produce text.
Give tools meaningful function and parameter names, and provide semantic guidance where it helps make their purpose clear. A descriptive tool name such as get_current_time gives the model more useful context than a vague name such as do_thing. Parameters should likewise say what information they represent. A tool should return the result the model needs to answer, rather than relying on the model to infer facts that the program could retrieve directly.
The example output depends on the model backend and the time at which it runs. Treat the code as a documented usage pattern, not a promise of exact wording or a claim that a particular run was performed. A model may phrase the response differently while using the returned time value.
What is jac ai?
jac ai is Jac’s built-in coding agent command, not the same thing as the AI-agent function you just wrote. It launches an assistant in a project that can use configured or local models, read built-in guides, edit files, and run code. That makes it a separate CLI workflow for working on a project, rather than a function in your Jac application that exposes selected tools to an LLM.
Recommended Free Tools
The documentation describes a --safe option that requires approval for each file write and command execution. If you explore the coding agent, understand those permissions before using it in a project: approval prompts are a control over its actions, not a substitute for reviewing the changes or commands. The first tool-using Jac script in this guide does not require jac ai.
Single-file script or full project?
For a first local program, use a standalone .jac file and run jac run <file>. The official getting-started material also covers creating and starting broader applications, but jac create and jac start are intended for a larger app workflow, not prerequisites for this first agent. Start with the smallest path that answers your question; scaffold an application when you actually need its broader structure.
Rank #4
- 【Softer and More Comfortable】Vaydeer wrist rest has unique diamond pattern, which is the combination of softness and aesthetics. The materials of wrist rest are improved into higher quality memory foam and covered with silky smooth lycra. The computer wrist rest makes you as comfortable and cushiony as like rest your wrists on clouds.
- 【Ergonomic Wrist Saver】The wrist rests for keyboard and mouse comes with a 17.32×3.15×0.83 inch keyboard wrist pad and a 5.94×3.15×0.83 inch mouse wrist support. Based on ergonomic design, the unique concave shape is the perfect fit for your wrist joints. The wrist rest pad fits most computer keyboards and laptops, improve hand and wrist posture, release your wrist and arm stress.
- 【Non-Slip Rubber Bottom】Featuring an anti-skid silicone base on the bottom, this wrist keyboard support stays firmly in place on your desk, preventing the padding from sliding around, ensuring stable and consistent wrist support during extended computer sessions.
- 【Better Experience & Pain Relief】Our keyboard arm rest is beneficial to alleviate the soreness caused by direct contact and friction between your arm and a hard desk surface, reducing the risk of wrist fatigue or carpal tunnel. The soft texture of memory foam can evenly distribute the pressure around your wrists and provide good support with just enough give.
- 【Helpful in Multiple Scenarios】Whether you're working, studying, writing, typing, gaming, this keyboard and mouse rest combo is an essential accessory to add comfort and support to your hands and wrists. It’s also a great gift for men, women, family, friend, coworker, gamer, teacher, etc.
If you want to use Docker instead of installing the CLI directly on the host, the official installation page documents the jaseci/jaclang image. Its example runs a project from the working directory, mounts that directory into /app, and runs jac run main.jac. Consult the current Docker instructions for the complete invocation and image details. Docker is an installation alternative, not an additional requirement for a standard local install.
The install page also lists an AUR package named jaclang for Arch Linux users. That is another route to the CLI; follow the package’s current instructions and do not run the shell installer as well unless your environment calls for it. The official shell installer, AUR route, and Docker image are alternatives, not steps to combine into one installation.
Free tools Windows power users keep installed
One-click scans. No signup required.
Troubleshoot the first run
-
jac --versionis not found: the shell cannot locate the CLI. Confirm the install completed and that Jac’s binary is on PATH. Use the current official installation guidance for your shell or platform. -
The basic file works but the AI function fails: the CLI itself may be fine; check that you ran
jac install byllmfor the project and that your chosen backend is configured. -
A hosted call reports a credential issue: check that the matching provider key is set in the environment of the process running Jac. Confirm you have selected the intended provider and model, and consult that provider’s current key instructions.
-
An Ollama call cannot reach the model: verify that Ollama is installed and running, that the example model has been pulled, and that the configuration’s model identifier matches the model you selected.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy. -
The local runtime downloads a large file: the documented in-process path downloads a model of about 5 GB on first use. Check available connection and storage capacity and allow the initial download to finish.
-
The file reports an error or warning: Jac’s getting-started guide documents diagnostic output with
jac -e all hello.jac. Use it to inspect errors and warnings for the file, then address the reported issue before adding more agent behavior. -
You are trying to run a one-file tutorial with app commands: use
jac run first_agent.jacfor the standalone script. App scaffolding commands serve the broader application workflow.
Keep the layers separate while debugging: installation gets the jac command running; project dependency resolution prepares optional byLLM packages; backend configuration makes a model available; and the Jac file defines what the model can do. Testing the hello-world file first helps identify whether a failure comes from the language installation or from the later AI setup.
Free tools Windows power users keep installed
One-click scans. No signup required.
Time and setup expectations
Jaseci Labs’ installation guide describes its install as under two minutes, its AI quickstart estimates about 20 minutes, and its agent tutorial estimates about 45 minutes. These are the publisher’s estimates for the documented guides, not measured guarantees. Your actual setup depends on the selected backend: a hosted path requires provider configuration, Ollama requires a separate installation and model pull, and the in-process local option can download about 5 GB on first use.
Best Value
- 【No Drill Mounted】Cable management tray can be assembled in as little as 3 minutes or less-simply. Side clips easily clampe the edge of desk, pass through the holes on the sides, and secure excess cables with baskets. Desk cable management supports inward or outward installation to meet your needs in different scenarios, and provides you with great convenience when collecting and organizing wires.
- 【Rubber Pad Protects Desk】Wire organizer under desk built-in soft rubber pads on the clamp protect your desk from scratches, so you will not damage your furniture or office.
- 【Sturdy and Beautiful】Cord management under desk is made of high-quality carbon steel and holds about 15 lbs. The wire basket has 2 holes on each side of the tray to enable your cables to pass freely. Cable baskets are suitable for desk thickness use from 0.4" to 2.4".
- 【Space Saving & Keep Organized】Desk cable management tray holds all your power cords, outlet strips, USB hubs and computer transformers hidden from your feet, and the data cables will not enter the vacuum cleaner to keep your desk clean and tidy. Desk wire organizer is also suitable for use in the kitchen and outdoors.
- 【Reduce Safety Risks】Cable tray under desk keeps all plugs away from your kids, no more worry about tripping. Using 2 holes wire tray saves extra space, helps you easily cabling and wire protection. The mesh design is not easy to accumulate dust, but avoids safety accidents caused by messy wires.
No price figures or comparative performance claims are established by the cited setup material. Provider plans and local hardware needs are outside the Jac CLI installation steps; consult the current service or runtime instructions for your own setup rather than treating one model path as universally free, fastest, or easiest.
Frequently Asked Questions
Do I need Python, pip, or uv to install Jac?
The recommended installer downloads a self-contained native Jac binary. The official installation page says system Python, pip, and uv are not needed to install or run that binary. Optional AI dependencies and a selected inference backend may still require additional setup.
Does installing Jac give me an AI model or API key?
No. Installing Jac gives you the CLI and includes byLLM capability, but a project may need optional dependencies resolved with jac install byllm. AI-backed calls also need a configured hosted provider credential or a local inference option such as Ollama or the optional in-process runtime.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsWhat is the shortest way to run a Jac file?
Create a .jac file with a with entry block and run it with jac hello.jac or jac run hello.jac. A basic hello-world program does not require a model backend.
What makes the sample an AI agent rather than a regular LLM call?
The LLM-backed function receives an ordinary Jac function in tools=[get_current_time]. The model can choose to call that tool, use its result, and formulate an answer. A plain LLM-backed function without tools is a smaller checkpoint but does not demonstrate tool use.
Which local backend should I choose: Ollama or the in-process runtime?
The Jac guide recommends Ollama, which is installed separately and runs as a service; its example pulls gemma3:4b and configures it as ollama/gemma3:4b. The optional in-process runtime avoids a separate daemon but downloads a model of about 5 GB on first use. Choose based on whether you prefer a separate service or an in-process setup and can accommodate the initial download.
Is jac ai the same as writing a Jac agent program?
No. jac ai launches Jac’s built-in coding agent, which can work with project files and run code. The tutorial program is an LLM-backed Jac function that exposes developer-defined functions as tools. The documentation says jac ai --safe requires approval for file writes and command execution.
Recommended Free Tools
Do I need to run jac create or jac start first?
No. Those commands are for a broader app workflow. For a standalone first program, save a Jac file and run jac run <file>.
Can I install Jac with Docker or an AUR package instead?
Yes. The official installation page documents an AUR package called jaclang and a Docker image called jaseci/jaclang. They are alternatives to the shell installer. Follow the current instructions for the route and platform you choose.
How much does it cost to run the example?
The cited Jac setup documentation does not give prices or a comparative cost estimate. Hosted provider charges, if any, depend on the provider and its current terms; the documentation does not establish a universal cost for local inference either.
The Bottom Line
Install Jac, verify the CLI, resolve byLLM dependencies, and choose a hosted or local model backend. Then run a standalone .jac file whose LLM-backed function receives an ordinary Jac function as a tool. The language installation and the model setup are separate steps, and jac ai is a separate coding-agent feature rather than the program you just built.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
