PyPI · npm
ComposioHQ/composio
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
MITSep 16, 2026 · metrics 2.10.0
All tags
Catalogue tag
#function-calling
Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.
40 records
npm
TanStack/ai
🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.
MITSep 12, 2026 · metrics 2.10.0
PyPI · npm
NVIDIA-NeMo/Gym
Evaluate and improve models and agents using environments
Apache-2.0Sep 10, 2026 · metrics 2.10.0
npm · PyPI
QVerisAI/qveris-agent-toolkit
Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs for agents to discover, inspect, call, and audit real-world tools.
MITSep 9, 2026 · metrics 2.10.0
npm · PyPI
mohitagw15856/pm-claude-skills
1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in Anthropic's plugin directory. Plus a typed decision layer: which skill, is it safe, ship or slip. Free in-browser or npx pm-claude-skills add.
MITOct 20, 2026 · metrics 2.10.0
npm · Go
corsairdev/corsair
Connect your users to their apps
Custom licenseSep 18, 2026 · metrics 2.10.0
npm
withcatai/node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
MITAug 27, 2026 · metrics 2.10.0
PyPI
Tejas-TA/predikit
The missing bridge between your ML models and your AI agents.
MITSep 15, 2026 · metrics 2.10.0
npm
equationalapplications/expo-llm-wiki
Offline-first, SQLite-backed, tiered, multi-entity memory for LLM apps built with Expo, React, Node, or plain JS
MITSep 10, 2026 · metrics 2.10.0
PyPI · npm
Klavis-AI/klavis
Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Apache-2.0Sep 19, 2026 · metrics 2.10.0
Go
liushuangls/go-anthropic
Anthropic Claude API wrapper for Go
Apache-2.0Sep 5, 2026 · metrics 2.10.0
npm · crates.io
stella/folio
Framework-neutral DOCX engine with React/Vue editors, Nuxt integration, and agent tooling
Apache-2.0Sep 9, 2026 · metrics 2.10.0
npm
webgptorg/promptbook
Turn your company's scattered knowledge into AI ready Books ✨
Custom licenseSep 6, 2026 · metrics 2.10.0
Go
amit-timalsina/pi-llm-go
Minimal Go LLM client (v1.0, stable). Streaming, strict tool calling, adaptive extended thinking, prompt caching, token counting, cost helpers, retry middleware. Anthropic Claude, OpenAI (GPT-5 + Responses), Google Gemini, OpenAI-compatible hosts.
Custom licenseSep 15, 2026 · metrics 2.10.0
PyPI
myriade-ai/agentlys
Lightweight AI agent library. Turn Python functions/classes into AI tools instantly. No verbose configs or complex abstractions.
MITSep 9, 2026 · metrics 2.10.0
PyPI · npm
SonAIengine/graph-tool-call
Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.
MITSep 15, 2026 · metrics 2.10.0
npm · crates.io
tetsuo-ai/agenc-protocol
Public protocol source of truth for AgenC: Anchor program, zkVM guest, migrations, and generated protocol artifacts
GPL-3.0Sep 15, 2026 · metrics 2.10.0
—
tryAGI/CSharpToJsonSchema
Source generator to convert C# interfaces to JSON Schema for AI tool calling
MITOct 20, 2026 · metrics 2.10.0
PyPI
hahalee000000/helen
Helen Agent Develop Language
MITSep 14, 2026 · metrics 2.10.0
npm
arikusi/deepseek-mcp-server
MCP server for DeepSeek V4 (v4-flash, v4-pro, 1M context): chat, reasoning, function calling, thinking mode, cost tracking. deepseek-chat/reasoner aliases supported.
MITOct 14, 2026 · metrics 2.10.0
npm
bytesbrains/weblocks
Block engine for AI-composable web apps — snap-together 'Lego' blocks + the AI catalog contract (manifest → validate → render static HTML).
MITSep 17, 2026 · metrics 2.10.0
Go
hung12ct/gopheragent
Go/Golang multi-agent LLM framework — ReAct loops, parallel tool calls, streaming, sub-agents, and pluggable Anthropic / OpenAI / Gemini providers.
Apache-2.0Sep 13, 2026 · metrics 2.10.0
npm
igorls/universal-llm-client
No repository description published.
MITSep 15, 2026 · metrics 2.10.0
Go
psyb0t/elelem
A Go engine for talking to LLMs that doesn't give a shit which one. Streaming, tool loops, history that actually fits the context window, retries that don't repeat themselves, and typed structured output. Swap OpenAI for Anthropic by changing one line. Library, not a framework: you own the loop.
MITOct 19, 2026 · metrics 2.10.0
npm
therealtimex/node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
MITSep 10, 2026 · metrics 2.10.0
npm
useago/ago-sdk
Create agents that helps your customers right into your apps
Apache-2.0Sep 9, 2026 · metrics 2.10.0
PyPI
ainiadra/niadra-sdk-python
Python SDK for Niadra: shared customer memory for every AI agent in a company. Context before the model call, history, tools and MCP.
Apache-2.0Oct 5, 2026 · metrics 2.10.0
Go
dotcommander/jinn
Sandboxed JSON-over-stdin/stdout tool executor for AI coding agents with 19 tools, workspace confinement, and guarded mutation.
MITSep 13, 2026 · metrics 2.10.0
PyPI
QwenLM/Qwen-Agent
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Apache-2.0Sep 17, 2026 · metrics 2.10.0
npm · crates.io · Maven
arusatech/llama-cpp-pro
Llama cpp + CapacitorJS support
MITSep 15, 2026 · metrics 2.10.0