#llm

Опис репозиторію не опубліковано.

CLI that auto-detects AI provider credentials and shows usage quotas in a TUI or JSON

Опис репозиторію не опубліковано.

A modern bun framework that is easy and AI first

Blazing fast Go port of gemini-web2api. Convert Google Gemini web into OpenAI-compatible API. Zero cost, single static binary.

Plugin lifecycle manager for the intisy-ai AI-proxy ecosystem.

Schedule, run, and track AI agents with zero infra.

Governed AI agents that actually do the work - in the cloud or on your own machine - across business systems, real browser tabs and real Android apps. Visual builder, MCP server, and official SDKs in 9 languages.

Elixir SDK for the Amp CLI — provides a comprehensive client library for interacting with Amp's AI-powered coding agent, including thread management, tool orchestration, streaming responses, and programmatic access to Amp's full feature set from Elixir/OTP applications

Parse partial JSON generated by LLM

TypeSafe platform bridge for Symfony AI

ClickUp MCP Server - Integrate ClickUp project management with AI through Model Context Protocol

A stateful, graph-based agent runtime for Go — LangGraph's core ideas in 419 dependency-free lines

Evaluate LLMs side-by-side. Benchmark AI models and coding agents across providers like OpenAI, Google, Anthropic, DeepSeek, and more. Supports custom tasks, structured JSON responses, tool use, and LLM-as-judge validation. Originally created by Petr Malik as MindTrial.

Adversary simulation and Red teaming platform with AI

Deterministic, LLM-agnostic scaffolding CLI with adapters for Claude Code and GitHub Copilot CLI. Generates boilerplate code while letting AI agents focus only on business logic.

test

Опис репозиторію не опубліковано.

Unified LLM client library for Go - one API, 36 providers (Anthropic, OpenAI, Google Gemini, AWS Bedrock, Mistral, Groq, DeepSeek, +29 more), zero external dependencies.

Опис репозиторію не опубліковано.

An isolated, secure execution sandbox for AI coding agents

Switch Claude Code's backend per terminal — one command, no global config.

Zero-dependency prompt compression for LLM applications. One deterministic algorithm, three native SDKs (TypeScript/Bun, Rust, Go) with byte-identical output. No ML model, no downloads.

CLI tool that explains programming errors using a locally-embedded LLM. No API keys. No internet. No patience required.

Adaptive JSON-to-agent terminal output with exact token-aware format selection

A local MITM proxy between AI coding agents and their APIs: it masks secrets found in outbound prompts with shape-preserving surrogates and restores them in the response. Go, runs entirely on your machine.

Turns a plain folder into a persistent, evidence-first memory: episodic recall with cite-or-abstain answers, distilled convictions, and a deterministic constraint shield. Go library plus CLI, offline, git as the audit trail.

Pi Agent extension that bridges MCP servers to the LLM via two dynamic-context tools (CallMcpTool + FetchMcpResource). Filesystem-is-everything: each MCP server is described by meta.json + tools/*.json, loaded into context on session start.

Fast WebGPU runtime for 1-bit (binary-weight) LLMs in the browser. Bit-exact, zero runtime dependencies.

Self-hosted AI gateway — route, observe, and control your LLM API traffic. OpenAI ↔ Anthropic protocol translation, cost-based smart routing, per-user budgets, built-in dashboard. Zero dependencies.