Veracium
Veracium – agent memory keeping third-party claims from becoming facts
Open-source projects. Clever little tools. Big ideas.
Unearthed from the Hacker News community.
Veracium – agent memory keeping third-party claims from becoming facts
ProtoLink – A Python runtime for distributed A2A agents
NMEMORY – A memory for AI agents that refuses to answer without evidence
EdgeRunner – run GGUF models with Swift and Metal
Ctoken – CLI util to count LLM tokens in files, dirs or input
Snitch – Deterministic prose claim verifier for coding agents. (OSS)
STT-MCP – local STT for agents
Awsmux – Multi-account AWS CLI, up to 5.4x faster, 7.4x fewer tokens
a Rust OS kernel built for LLM inference
Explain this – agent skills to create HTML explainer for topics or code
Ankole – Claude Tag open source alternative
Remortgaging with Claude, so I built a MCP for Bank of England
Sieze the means of production from our agentic overlords
Claudexor – quota-aware routing for Claude Code, Codex, and Cursor
How you auto recover your Claude Code workflow when quota resumes
Otari: your open-source LLM control plane
WiFi-LLM
ClaudeFS – Give claude.ai access to a local folder, no local process