A free, open-source Chrome extension called Usage Bar for Claude displays Claude plan usage limits, a live token counter for the context window, and a prompt-cache countdown directly on claude.ai. The…
GigaToken, a new open-source tokenizer, claims to be up to ~1000x faster than HuggingFace's tokenizers and tiktoken for language model tokenization, achieving speeds of over 24 GB/s on an AMD EPYC 956…
An engineer shared a Python script, agent_expanded.py, that implements a simple agent loop for a large language model with a 1,050,000-token context window. The script uses a custom shell tool to exec…
A developer created claude-hist, a command-line tool that uses fzf to fuzzy-find and resume past Claude Code sessions across all projects. The tool searches session titles, git branches, and conversat…
Finterm AI released an open-source Investment Skills Lexicon that distills Warren Buffett's investment framework from 72 primary documents (950,000 words) into 65 evidence-bounded decision cards for u…
Hwatu, a daemon-based WebKit browser for tiling window managers, achieves a median window spawn time of 13 milliseconds (p90 35 ms) on a warm daemon by splitting the browser engine from the window, ac…
VifuDev released Vifu, an open-source game runtime for building AI-native games, under Apache-2.0. The runtime includes a Rust executable, Agent Gateway protocol, PostgreSQL database, and Next.js dash…
A benchmark comparing LLM Gateway and OpenRouter for Claude Haiku 4.5 found LLM Gateway is ~35% faster to first token cold (906 vs 1392ms) and ~34% faster warm (814 vs 1232ms) at the median. The TTFB …
A developer created a Hammerspoon script that enables click-through on macOS, allowing users to interact with UI elements in inactive windows without first selecting the window. The script, built with…
EcoTrace v1.4.0, a lightweight Python library for real-time carbon footprint tracking of applications, has been released with new features including a pausable tracking API, WebhookExporter for stream…
Veracium, a provenance-aware memory plug-in for agentic systems, launches to resist injection and confabulation failures in naive agent memory by storing third-party claims as structurally quarantined…
Yorishiro, a new macOS terminal that gives AI agents a visual presence and real-time environmental control, has been released. The tool, which launches Claude Code or Codex inside its interface, featu…
Srenix, an open-source self-healing Kubernetes tool released under Apache-2.0, diagnoses and fixes cluster faults using a 30MB Go binary with 16 Kubernetes probes, 14 read-only analyzers, 30 cloud pro…
A developer achieved ~28 tok/s single-stream decode of DeepSeek-V4-Flash (284B MoE) on a single RTX 5090 with dual Xeon Gold 6138 CPUs using a CPU-offloaded expert recipe. The setup uses ktransformers…
Helical Insight, an open source BI platform, announced that all features including a new AI module, SSO, embedding, multi-tenancy, and row-level security are now free in its Community Edition, with th…
Looperators, a new tool for AI coding agents, places agents on a visual canvas connected by executable edges that automatically move context, trigger agents, and decide when loops finish, eliminating …
QAgent, a self-healing QA agent that automatically tests web applications, identifies bugs, applies fixes, and verifies fixes without human intervention, has been released as an open-source project on…
An engineer created a minimal AI agent in just 9 lines of Python code, using a custom tool to execute shell commands and a loop that processes user input through a language model. The agent, which cal…
PortMarshal, a new open-source command-line tool for macOS and Linux, prevents parallel coding agents from accidentally stopping each other's local development servers by mapping TCP listeners to thei…
A new open-source MCP server called talkthrough-mcp, released under the MIT license, lets developers turn narrated screen recordings into structured data for AI agents without any cloud dependency. Th…