A developer known as Avifenesh released Bw24, a from-scratch LLM inference engine in Rust and CUDA tuned for NVIDIA's RTX 5090 Laptop GPU (Blackwell sm_120a, 24 GB), achieving up to 2.3x speedup over …
A developer created a PowerShell script to recover Claude Code Desktop sessions that are missing from the sidebar on Windows. The script scans ~/.claude/projects/ for .jsonl files and generates local_…
A new open-source project called 'thoughts' provides coding agents with a selective, durable memory system that survives context loss by maintaining a searchable THOUGHTS.md scratchpad for non-obvious…
Traccia SDK, an open-source execution evidence layer for AI agents, has been released under the Apache 2.0 license. The tool records autonomous agent behavior to make it provable, reproducible, and au…
Pkgxray, a pre-install security tool for npm packages, MCP servers, and AI agents, uses static analysis to inspect packages before installation, reporting SAFE, REVIEW, or BLOCK verdicts without execu…
NOTT, an AI agent, released nMEMORY, a single-file memory store that refuses to fabricate answers when it lacks evidence, abstaining instead of guessing. The tool runs entirely on the user's machine w…
Akili released v0.1.0-rc4, a continual-learning runtime that gates skill updates and provides rollback receipts for deployed models. The runtime achieved 99.5% overall mean across 4 skills × 3 seeds o…
Agent Atlas, an open-source tool that maps AI coding environments, reveals that 90 of 103 installed skills never fire, based on an analysis of Claude Code setups. The tool scans configuration and sess…
A developer released add-reasoning-to-prs, a hook for Claude Code that extracts decisions, assumptions, and trade-offs from session transcripts and appends them to pull request descriptions, aiming to…
Telize, a terminal-first YAML runner for chaining shell, Python, file I/O, and LLM steps, has been released as an open-source alpha (version 0.4.0) under Apache 2.0. Unlike agent frameworks such as La…
A developer has released Hypr Realm, an experimental fork of the Hyprland Wayland compositor that enables AI agents to operate in parallel, visible nested desktops without interfering with the human u…
A new open-source command-line tool called Gml gives coding agents and shell workflows direct access to Gmail without a daemon, browser automation, or an SDK integration. Created by developer LongyiJd…
A developer released ckg-agentforce, an open-source tool that represents Salesforce AgentForce as a traversable knowledge graph with 40 nodes and 52 edges, enabling deterministic, auditable answers ab…
RunKit, a browser-based tmux manager from the shll toolkit, launches as a remote console that exposes live tmux sessions and panes in a sidebar, designed to let users monitor multiple AI coding agents…
A new open-source CLI client called mcp-console supports two OAuth 2.0 authentication strategies for Model Context Protocol servers: CIMD (Client ID Metadata Document) and DCR (Dynamic Client Registra…
The MCP 2026-07-28 revision introduces Multi Round-Trip Requests (MRTR), a breaking change that invalidates latency measurements in observability tools by requiring separate JSON-RPC IDs for each leg …
NanoNets released Ami, an open-source AI agent that runs locally on a user's machine and acts as a personal clone by connecting to apps, data, and tools via personal tokens. The agent maintains a live…
Drey, an open-source LSP multiplexer, lets multiple editors and coding agents share a single language server per workspace to reduce memory usage, as demonstrated by two Claude Code sessions on one Ru…
A developer has released a proof-of-concept for a deterministic governance harness that validates LLM-generated code against policies, aiming to increase confidence in autonomous code generation. The …
A developer argues that major AI companies are deliberately suppressing advanced sampling techniques like min-p, mirostat, and dynamic temperature, offering users only basic controls while hobbyist to…