llm-functions

Name: llm-functions
Author: sigoden

762stars131forks

How to install llm-functions?

sigoden/llm-functions

$git clone https://github.com/sigoden/llm-functions

Installs into the current project.

Summary

This project empowers you to effortlessly build powerful LLM tools and agents using familiar languages like Bash, JavaScript, and Python.

Files · 1

View on GitHub

README.md

1	# LLM Functions
2
3	This project empowers you to effortlessly build powerful LLM tools and agents using familiar languages like Bash, JavaScript, and Python.
4
5	Forget complex integrations, harness the power of [function calling](https://platform.openai.com/docs/guides/function-calling) to connect your LLMs directly to custom code and unlock a world of possibilities. Execute system commands, process data, interact with APIs – the only limit is your imagination.
6
7	Tools Showcase
8	![llm-function-tool](https://github.com/user-attachments/assets/40c77413-30ba-4f0f-a2c7-19b042a1b507)
9
10	Agents showcase
11	![llm-function-agent](https://github.com/user-attachments/assets/6e380069-8211-4a16-8592-096e909b921d)
12
13	## Prerequisites
14
15	Make sure you have the following tools installed:
16
17	- [argc](https://github.com/sigoden/argc): A bash command-line framework and command runner
18	- [jq](https://github.com/jqlang/jq): A JSON processor
19
20	## Getting Started with [AIChat](https://github.com/sigoden/aichat)
21
22	Currently, AIChat is the only CLI tool that supports `llm-functions`. We look forward to more tools supporting `llm-functions`.
23
24	### 1. Clone the repository
25
26	```sh
27	git clone https://github.com/sigoden/llm-functions
28	cd llm-functions
29	```
30
31	### 2. Build tools and agents
32
33	#### I. Create a `./tools.txt` file with each tool filename on a new line.
34
35	```
36	get_current_weather.sh
37	execute_command.sh
38	#execute_py_code.py
39	```
40
41	<details>
42	<summary>Where is the web_search tool?</summary>
43	<br>
44
45	The `web_search` tool itself doesn't exist directly, Instead, you can choose from a variety of web search tools.
46
47	To use one as the `web_search` tool, follow these steps:
48
49	1. Choose a Tool: Available tools include:
50	* `web_search_cohere.sh`
51	* `web_search_perplexity.sh`
52	* `web_search_tavily.sh`
53	* `web_search_vertexai.sh`
54
55	2. Link Your Choice: Use the `argc` command to link your chosen tool as `web_search`. For example, to use `web_search_perplexity.sh`:
56
57	```sh
58	$ argc link-web-search web_search_perplexity.sh
59	```
60
61	This command creates a symbolic link, making `web_search.sh` point to your selected `web_search_perplexity.sh` tool.
62
63	Now there is a `web_search.sh` ready to be added to your `./tools.txt`.
64
65	</details>
66
67	#### II. Create a `./agents.txt` file with each agent name on a new line.
68
69	```
70	coder
71	todo
72	```
73
74	#### III. Build `bin` and `functions.json`
75
76	```sh
77	argc build
78	```
79
80	#### IV. Ensure that everything is ready (environment variables, Node/Python dependencies, mcp-bridge server)
81
82	```sh
83	argc check
84	```
85
86	### 3. Link LLM-functions and AIChat
87
88	AIChat expects LLM-functions to be placed in AIChat's functions_dir so that AIChat can use the tools and agents that LLM-functions provides.
89
90	You can symlink this repository directory to AIChat's functions_dir with:
91
92	```sh
93	ln -s "$(pwd)" "$(aichat --info \| sed -n 's/^functions_dir\s\+//p')"
94	# OR
95	argc link-to-aichat
96	```
97
98	Alternatively, you can tell AIChat where the LLM-functions directory is by using an environment variable:
99
100	```sh
101	export AICHAT_FUNCTIONS_DIR="$(pwd)"
102	```
103
104	### 4. Start using the functions
105
106	Done! Now you can use the tools and agents with AIChat.
107
108	```sh
109	aichat --role %functions% what is the weather in Paris?
110	aichat --agent todo list all my todos
111	```
112
113	## Writing Your Own Tools
114
115	Building tools for our platform is remarkably straightforward. You can leverage your existing programming knowledge, as tools are essentially just functions written in your preferred language.
116
117	LLM Functions automatically generates the JSON declarations for the tools based on comments. Refer to `./tools/demo_tool.{sh,js,py}` for examples of how to use comments for autogeneration of declarations.
118
119	### Bash
120
121	Create a new bashscript in the [./tools/](./tools/) directory (.e.g. `execute_command.sh`).
122
123	```sh
124	#!/usr/bin/env bash
125	set -e
126
127	# @describe Execute the shell command.
128	# @option --command! The command to execute.
129
130	main() {
131	eval "$argc_command" >> "$LLM_OUTPUT"
132	}
133
134	eval "$(argc --argc-eval "$0" "$@")

People who liked this also viewed

6 picks

Type

fastapi_mcpExpose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!MCP ServersNov 202519M12k
lean-lsp-mcpLean Theorem Prover MCPMCP ServersJul 20261.9M454
rulesyncA Utility CLI for AI Coding AgentsMCP ServersJul 2026889k1.3k
FunASROpen-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.MCP ServersJul 2026443k19k
repomix📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.MCP ServersJul 2026310k27k
mcp-serverMCP server for AI-assisted development of CAP applicationsMCP ServersJul 2026295k105

llm-functions

762stars131forks

View on GitHub

How to install llm-functions?

sigoden/llm-functions

$git clone https://github.com/sigoden/llm-functions

Installs into the current project.

Summary

This project empowers you to effortlessly build powerful LLM tools and agents using familiar languages like Bash, JavaScript, and Python.

Files · 1

View on GitHub

README.md

1	# LLM Functions
2
3	This project empowers you to effortlessly build powerful LLM tools and agents using familiar languages like Bash, JavaScript, and Python.
4
5	Forget complex integrations, harness the power of [function calling](https://platform.openai.com/docs/guides/function-calling) to connect your LLMs directly to custom code and unlock a world of possibilities. Execute system commands, process data, interact with APIs – the only limit is your imagination.
6
7	Tools Showcase
8	![llm-function-tool](https://github.com/user-attachments/assets/40c77413-30ba-4f0f-a2c7-19b042a1b507)
9
10	Agents showcase
11	![llm-function-agent](https://github.com/user-attachments/assets/6e380069-8211-4a16-8592-096e909b921d)
12
13	## Prerequisites
14
15	Make sure you have the following tools installed:
16
17	- [argc](https://github.com/sigoden/argc): A bash command-line framework and command runner
18	- [jq](https://github.com/jqlang/jq): A JSON processor
19
20	## Getting Started with [AIChat](https://github.com/sigoden/aichat)
21
22	Currently, AIChat is the only CLI tool that supports `llm-functions`. We look forward to more tools supporting `llm-functions`.
23
24	### 1. Clone the repository
25
26	```sh
27	git clone https://github.com/sigoden/llm-functions
28	cd llm-functions
29	```
30
31	### 2. Build tools and agents
32
33	#### I. Create a `./tools.txt` file with each tool filename on a new line.
34
35	```
36	get_current_weather.sh
37	execute_command.sh
38	#execute_py_code.py
39	```
40
41	<details>
42	<summary>Where is the web_search tool?</summary>
43	<br>
44
45	The `web_search` tool itself doesn't exist directly, Instead, you can choose from a variety of web search tools.
46
47	To use one as the `web_search` tool, follow these steps:
48
49	1. Choose a Tool: Available tools include:
50	* `web_search_cohere.sh`
51	* `web_search_perplexity.sh`
52	* `web_search_tavily.sh`
53	* `web_search_vertexai.sh`
54
55	2. Link Your Choice: Use the `argc` command to link your chosen tool as `web_search`. For example, to use `web_search_perplexity.sh`:
56
57	```sh
58	$ argc link-web-search web_search_perplexity.sh
59	```
60
61	This command creates a symbolic link, making `web_search.sh` point to your selected `web_search_perplexity.sh` tool.
62
63	Now there is a `web_search.sh` ready to be added to your `./tools.txt`.
64
65	</details>
66
67	#### II. Create a `./agents.txt` file with each agent name on a new line.
68
69	```
70	coder
71	todo
72	```
73
74	#### III. Build `bin` and `functions.json`
75
76	```sh
77	argc build
78	```
79
80	#### IV. Ensure that everything is ready (environment variables, Node/Python dependencies, mcp-bridge server)
81
82	```sh
83	argc check
84	```
85
86	### 3. Link LLM-functions and AIChat
87
88	AIChat expects LLM-functions to be placed in AIChat's functions_dir so that AIChat can use the tools and agents that LLM-functions provides.
89
90	You can symlink this repository directory to AIChat's functions_dir with:
91
92	```sh
93	ln -s "$(pwd)" "$(aichat --info \| sed -n 's/^functions_dir\s\+//p')"
94	# OR
95	argc link-to-aichat
96	```
97
98	Alternatively, you can tell AIChat where the LLM-functions directory is by using an environment variable:
99
100	```sh
101	export AICHAT_FUNCTIONS_DIR="$(pwd)"
102	```
103
104	### 4. Start using the functions
105
106	Done! Now you can use the tools and agents with AIChat.
107
108	```sh
109	aichat --role %functions% what is the weather in Paris?
110	aichat --agent todo list all my todos
111	```
112
113	## Writing Your Own Tools
114
115	Building tools for our platform is remarkably straightforward. You can leverage your existing programming knowledge, as tools are essentially just functions written in your preferred language.
116
117	LLM Functions automatically generates the JSON declarations for the tools based on comments. Refer to `./tools/demo_tool.{sh,js,py}` for examples of how to use comments for autogeneration of declarations.
118
119	### Bash
120
121	Create a new bashscript in the [./tools/](./tools/) directory (.e.g. `execute_command.sh`).
122
123	```sh
124	#!/usr/bin/env bash
125	set -e
126
127	# @describe Execute the shell command.
128	# @option --command! The command to execute.
129
130	main() {
131	eval "$argc_command" >> "$LLM_OUTPUT"
132	}
133
134	eval "$(argc --argc-eval "$0" "$@")

People who liked this also viewed

6 picks

Type