#llm

Building TITAN — the open-source AI operating system for trusted autonomous work: agents, tools, memory, approvals, receipts, voice, mission control, and SOMA. npm i -g titan-agent

Code intelligence for humans, machines, and LLMs: receipts, metrics, and insights from your codebase.

Universal LLM provider runtime — one interface for 75+ models. Authentication, routing, streaming, retries, rate limiting, and semantic caching.

🔥 Token-efficient JSON alternative for LLMs & agentic AI — same data, fewer tokens. Python · JS/TS · Rust · Go · C++

.NET MCP bridge: expose app methods/data as MCP tools, prompts, and resources via an in-app plugin + lightweight server (SignalR; stdio/http).

State of the Art Natural Language Processing

Reuse your Kimi Code (Moonshot) Coding plan inside pi-coding-agent

LLM gateway: tiered routing (local to frontier), mid-stream provider failover, and post-turn context curation, production-measured. Provider adapters are separate lex-llm-* gems.

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

GenAI OpenTelemetry Auto-Instrumentation Library A comprehensive wrapper for automatic instrumentation of LLM/GenAI applications Supports all major LLM providers and MCP (Model Context Protocol) tool calls

Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw

One Rust API to 25+ AI providers — chat, vision, tool calls, structured output, embeddings & reranking with built-in cost tracking

AI agent framework with Jupyter sandbox, data analysis, MCP tools, ACP protocol, multi-provider LLM, and standalone runtime packaging

The universal, platform-agnostic skills and capability registry for AI agents — mapping capabilities, skills, implementations, dependencies, evidence, and platform adapters across agent ecosystems.

Shared Go contract (Agent Passport + agent-event envelope) for the TAIPANBOX agent-governance stack

TradingAgents: Multi-Agents LLM Financial Trading Framework

Build with AI. Run with guarantees. TPF is a Java framework for strongly typed business flows that compose model decisions, authorised SaaS capabilities, and deterministic code—with durable effects, waits, retries, replay, observability, and flexible deployment.

Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs, and tools — the model handles its own control flow. Get fully interpretable trajectories and performance that scales directly with model improvements. Without context rot.

Yet Another Agent SDK, CLI, Claw, Agent Platform

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

The AI control plane for software development. Discovers every model on your machine, routes by capability and cost, enforces PII policy, tracks spend.

Native K-quant support for MLX, with a quantization and fine-tuning toolchain for Apple Silicon

a self improving operating system for intelligence

The easiest way to use Ollama in .NET

A local tool for humans to review AI generated code

Control Plane For Data Workflow With Built-In Agentic Remediation

Chat, specs, tasks, and code. An autonomous engineering platform. Full autonomy when you trust it. Full control when you don't.

45 MCP tools that give AI coding agents ground truth about your Rails app: schema, models, routes, controllers, views, jobs, conventions. Works with Claude Code, Cursor, GitHub Copilot, OpenCode and Codex CLI. MCP or CLI, in-Gemfile or standalone, and it still answers when the app can't boot.

The Data Control Plane for AI Agents — acquire, validate, and land data over MCP with scoped keys, approval gates, and an audit log. Self-hosted, open source.