A transparent (O)llama proxy with model deployment aware routing which auto-manages multiple (O)llama instances in a given network.
Updated 2026-06-17 19:41:50 +02:00
Updated 2026-06-17 14:57:46 +02:00
OpenAI compatible secure chat client with end-to-end encryption on NOMYO Inference Endpoints
Updated 2026-06-17 13:39:50 +02:00
A caching, resizing image proxy written in Go
Updated 2026-06-16 23:19:27 +02:00
An open source, privacy focused alternative to NotebookLM for teams with no data limit's. Join our Discord: https://discord.gg/ejRNvftDp9
Updated 2026-06-16 20:16:27 +02:00
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.
Updated 2026-06-16 16:12:11 +02:00
Lakehouse-native graph engine with git-style workflows
Updated 2026-06-16 03:35:18 +02:00
Cognitive memory for AI agents — FSRS-6 spaced repetition, 29 brain modules, 3D dashboard, single 22MB Rust binary. MCP server for Claude, Cursor, VS Code, Xcode, JetBrains.
Updated 2026-06-16 00:06:01 +02:00
Plano is an AI-native proxy and data plane for agentic apps — with built-in orchestration, safety, observability, and smart LLM routing so you stay focused on your agents core logic.
Updated 2026-06-15 23:25:55 +02:00
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.
Updated 2026-06-15 19:26:27 +02:00
ktx is the context layer for analytics agents
Updated 2026-06-15 17:23:59 +02:00
Multi-language static analysis with cross-file taint tracking. Scan your repo, triage findings in your browser, commit triage state with your code. No cloud, no account.
Updated 2026-06-15 12:42:43 +02:00
OSS AI Legal Platform
Updated 2026-06-15 11:45:31 +02:00
Hypernetworks that update LLMs to remember factual information
Updated 2026-06-15 06:31:47 +02:00
A high-performance, real-time ASCII video rendering engine. Streams binary-encoded frames via WebSockets for ultra-low latency, 60 FPS playback using HTML5 Canvas and requestAnimationFrame.
Updated 2026-06-14 20:27:34 +02:00
IAI-MCP fork to work with opencode plugin and qdrant db on non-AVX CPUs
Updated 2026-06-14 16:27:27 +02:00
fork of claude-for-legal ported to opencode
Updated 2026-06-13 15:38:37 +02:00
OpenAI compatible secure chat client with end-to-end encryption on NOMYO Inference Endpoints
Updated 2026-06-13 14:48:26 +02:00