Transparent proxy for multi-provider LLM cost tracking, budgeting, and optimization. Supports OpenAI, Anthropic, Azure, Bedrock, and Vertex AI with real-time cost headers.
Local LLM NPC is a privacy-first educational game featuring NPCs powered by Gemma 3n that teach sustainable farming, botany, and environmental topics through interactive conversations. All AI proce...
Kubernetes-native observability tool using eBPF to capture kernel signals and correlate them with OpenTelemetry traces for LLM SLO attribution.
Supply chain security for LLM artifacts using Sigstore, in-toto, and SLSA frameworks. Generates signed attestations for model weights, training data, and inference outputs.
Runtime firewall that detects and blocks prompt injection attacks against LLM applications. Covers OWASP LLM Top 10 attack vectors with configurable detection rules.
A self-evolving open source AI daemon written in Go. Learns through repetition, auto-generates code skills to replace expensive LLM calls, and generates unique visual interfaces from scratch for ev...
A debate-native, multi-agent AI framework for evidence-based reasoning with structured argumentation, decision-theoretic planning, and full provenance tracking. ARGUS implements the Research Debate...
BiasClear is open-source structural persuasion detection infrastructure for the AI ecosystem. It audits text for rhetorical manipulation patterns such as manufactured consensus, authority substitut...
Dual/tri-GPU multi-agent simulation framework. Orchestrates LLM-powered agents across GPU slots with FLAME population dynamics, Bayesian calibration (ABC-SMC), sensitivity analysis (Morris/Sobol), ...
Durable execution runtime for long-running AI agent workflows. Provides crash recovery, multi-provider LLM orchestration, human-in-the-loop approvals, cost tracking, and a TypeScript SDK. Built on ...
A fully local, open-source voice-to-text system with native overlay UI that converts speech into clean, formatted, context-aware text using Whisper.cpp and a local LLM.
A compact, self-hosted programming language for backend services, network tooling, and automation — built entirely on a Steam Deck. The full stack — lexer, parser, bytecode compiler, VM, and 3...
Neuroscience-inspired memory system for AI agents. Unlike passive vector stores, MemForge treats memory quality as something that should actively improve over time. It runs a 10-phase 'sleep cycle'...
Cognitive memory engine for AI agents. Sub-millisecond recall using Sparse Distributed Representations (SDR) instead of embeddings — no LLM calls, no cloud, no external dependencies. Pure Rust co...
Kindly Web Search is an MIT-licensed MCP server for AI coding agents such as Claude Code, Codex, Cursor, GitHub Copilot, Gemini, Windsurf, and OpenClaw. It combines web search with robust content r...
MIT-licensed Python framework providing the semantic intelligence layer that AI applications are missing — bridging raw text and trustworthy, explainable AI. Problem: Modern RAG pipelines and ag...
Computer use using local LLM models, which is private and secure by default
The first open-source Neurosymbolic AI Verification Layer. QWED prevents hallucinations in high-stakes LLM applications (Math, Finance, Logic) by using deterministic engines (SymPy, Z3, AST) to ver...
The first open-source Neurosymbolic AI Verification Layer. QWED prevents hallucinations in high-stakes LLM applications (Math, Finance, Logic) by using deterministic engines (SymPy, Z3, AST) to ver...
Open-source voice AI orchestration platform for Indian languages. Provides pluggable STT, TTS, LLM, and telephony providers with built-in cost tracking, per-call analytics, and DPDP compliance. Sup...
Ogulcan Aydogan
Code Forge Temple