Agent6, a new coding agent that jails model commands and uses editable state machines for long-running tasks, has been released. The agent restricts filesystem and network access via Landlock and secc…
Xaidr, a new open-source Python library, provides in-process runtime security and governance for AI agents, detecting prompt injection, jailbreaks, destructive tool calls, secret leakage, and protocol…
Rungraph, a new open-source tool, converts AI coding-agent transcripts into interactive directed graphs, allowing developers to visualize agent runs retroactively without hooks or setup. The tool, lau…
SwarmSim, a new open-source project posted on Hacker News, provides computational simulations of emergent flocking behavior. The project, available on GitHub, allows users to model and visualize how g…
A developer has released an early-stage Unixy LLM client that stores conversations using Git instead of SQLite, leveraging Git's immutable snapshots and commit structure to ensure data safety. The pro…
Andrew Sispoidis released an open benchmark of 497 attacks (395 visible plus 102 holdout) across 13 categories targeting LLM agents, with 1,172 benign samples for false-positive measurement. The tool-…
A developer's independent analysis of reasoning prefills on open models finds that Kimi K3 shows a significant accuracy increase on Humanity's Last Exam questions when prefilled with Opus 4.8 reasonin…
Offshoot, a new open-source tool, introduces copy-on-write branching for stock SQLite files, enabling AI agents and eval harnesses to fork databases instantly with minimal storage overhead. A shared f…
A developer reconstructed the source code for the 1994 Windows game Rats! using the local LLM Qwen3.8 27B BF16 on a 2024 MacBook Pro with an Apple M4 Max and 128 GB of memory, achieving an average rec…
Kungfu, an alpha-stage tool from Kungfu Systems, lets coding agents such as Codex, Claude, OpenCode, and Amp share durable work across sessions and handoffs, preserving objectives, progress, and evide…
A developer released a ~60-line shell hook that blocks AI coding agents from running irreversible commands like `git reset --hard`, `rm -rf`, and `DROP TABLE`, exiting with code 2 and writing the reas…
AetherGrid, a distributed AI compute orchestration system, has been released as an open-source project that manages AI workloads without Kubernetes, featuring time-bound leases for job execution owner…
HomeBrain, a new open-source appliance from developer oalterg, combines Nextcloud, Home Assistant, Vaultwarden, and a local AI agent into a single private cloud device with no subscriptions or cloud a…
Sol-Luna, an MCP server for OpenAI Codex, lets a supervising GPT-5.6 Sol agent delegate bounded implementation tasks to isolated GPT-5.6 Luna worker threads, with scope enforcement and verification. I…
Customhouse v0.2.0, a deterministic MCP proxy that blocks agent data exfiltration by tracking input provenance, reports a 100% block rate (11/11) over injection scenarios and a 40% false-positive rate…
A new open-source Rust project, tts-rs, delivers local text-to-speech on Apple silicon with three voice-cloning engines ported from PyTorch, achieving real-time factors as low as 0.252 for the Qwen3TT…
A new open-source PyTorch optimizer, the Riemannian Thermodynamic Optimizer, outperforms Adam on non-linear benchmarks by treating loss landscapes as physical topologies with Landauer dissipation and …
A developer released grafana-agento11y-hermes, an Apache-2.0 plugin that records LLM calls and tool executions from Hermes Agent as generations and emits OpenTelemetry traces and metrics to Grafana Cl…
Lucid, a new output style for Claude Code, reduces jargon and rambling to make responses easier to understand in one pass, lowering the reader's cognitive load. The style keeps coding instructions int…
PyScrappy, an AI-native web scraping toolkit that converts websites into structured, LLM-ready data, has been released as a Python library and MCP server, featuring self-healing selectors, JS renderin…