#llm

Local bridge for using OpenAI-compatible LLM providers with Codex and Claude coding clients.

kimi k2.7 terminal based coding agent & harness running on your own Cloudflare account.

Local context-compression layer for agent tool outputs. Claude Code PostToolUse hook or generic filter, single Go binary.

Run AI coding agents in parallel on one git repo and safely auto-merge their work — only changes that build and pass tests land. On top of plain git; bring your own model.

Generic platform bridge for Symfony AI

Ollama platform bridge for Symfony AI

Symfony bridge for AI Mate - provides Symfony container introspection and optional profiler data access tools

Google Vertex AI platform bridge for Symfony AI

A feature-full starting point for production agent applications on Tangle.

Understand your agent traces. Identify failures, get improvements.

🐍 Community-driven Python implementation of TOON

Official Go implementation of the UTCP

saige - Super Artificial Intelligence Graph Environment. A unified Go SDK, CLI, and MCP server for streaming AI agents, knowledge graphs, and RAG pipelines, with Ollama, OpenAI, Anthropic, and Google providers behind one interface.

LiteLLM for Go, the easiest way to write LLM-based programs in Go

Local CLI for diagnosing OpenAI- and Anthropic-compatible APIs beyond 200 OK with stream lifecycle checks and reproducible redacted reports.

VALORA (Versatile Agent Logic for Orchestrated Response Architecture) - The future of software development is not about replacing developers, but amplifying their capabilities with intelligent AI collaboration

Manage configs for Claude Code, Codex, Gemini CLI, Goose, and Amp from one repo — symlinks, merge pipeline, profile inheritance, cross-machine sync

A local-first, self-evolving terminal AI coding agent based on Pi — reads, edits, and runs code through conversation, and improves its own prompts and skills over time.

The WHY layer for AI agents: six constitutional gates + 12 hard constraints, plus cross-session risk composition — catches agents that pass every individual gate but accumulate risk across a sequence (stateless engines can't). pip install constitutional-agent

Self-hosted agentic OS — connects Claude Code, Codex or Hermes Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

Generate PDFs from JSON — declarative, serverless, no Chromium. TypeScript-first with professional typography.

Measure Claude Code and Codex usage. Get your Professional AI Usage Index, run-rate, tier, and verified shareable rank.

Terraform-style plan/apply for agent systems: versioned YAML for agents, tools, workflows, and policies; local-first SQLite state; MCP & HTTP tools; structured traces.

为 DeepSeek 前缀缓存定制的终端 Code Agent(纯 Go),缓存命中率 95-99%,命中输入定价为未命中的 1/30。A terminal coding agent optimized for DeepSeek prefix caching — 95-99% cache hit, cache-hit input priced at 1/30th of cache-miss.

Kubernetes operator for deploying and managing production-ready Langfuse LLM observability instances. Deploy the full stack (Web, Worker, PostgreSQL, ClickHouse, Redis, Blob Storage) from a single custom resource, with automated upgrades, secret rotation, multi-tenancy, and circuit breakers built in.

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Laravel-native client for Model Context Protocol (MCP) servers. Built by Redberry (Diamond-tier Laravel partner). Used by LarAgent and other frameworks to enable AI agent functionality.

Self-evolving skills lib for coding agents

🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.

🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.