← Back to articles

Show HN: AutoBot – live voice control for long-running AI work

2026-09-17 | original

read original get Jabra Evolve2 65 Wireless Headset → more articles

Why This Matters

AutoBot presents itself as a self-improving AI agent harness that claims to boost the task-completion abilities of existing frontier models like OpenAI's and Anthropic's on demanding, multi-application benchmarks, without retraining the underlying model. The claims of leaderboard-topping performance and self-repairing agent architecture are notable because they suggest a path toward more persistent, capable AI assistants that accumulate memory and improve over time, which could matter for both enterprise automation and consumer AI tools. As with many benchmark claims from new entrants, independent verification will be key to assessing how much of this holds up in practice.

Key Takeaways

AutoBot claims to outperform OpenAI and Anthropic baselines on OSWorld 2.0 and ranks #1 on the AssistantBench hidden-test leaderboard.
Its architecture emphasizes self-repair, persistent hierarchical memory, and task continuity across sessions and even across different AI workers.
It positions local compute (Mac-based orchestration) as an economical way to sustain long-running, persistent AI agents while it is open source and built by Autonomous Production.

Worth a Look

Jabra Evolve2 65 Wireless Headset — Since AutoBot is built around live voice control for long-running AI sessions, a reliable wireless headset with a noise-canceling mic makes those hands-free interactions much smoother. The Evolve2 65 is designed for all-day comfort and clear voice pickup, ideal for developers talking to their agents throughout the workday. It's a practical companion for anyone diving into voice-driven AI workflows.

See Jabra Evolve2 65 Wireless Headset on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.

Autobot

AutoBot: a self-improving agentic harness that makes frontier AI better at finishing complex knowledge work.

AutoBot achieved 18.5% higher task completion than the published OpenAI Sol Max baseline, surpassing Anthropic’s Claude Opus 5 Max on OSWorld 2.0, a benchmark of long, multi-application workflows. It also reached #1 on the official AssistantBench hidden-test leaderboard. Results and methodology

Hard workflows become upgrades to the agent itself. AutoBot repairs its own harness, independently validates the changes, and carries them forward. The next workflow inherits the improvement. Compounding capability, without retraining the model.

Your knowledge outgrows the context window. Hierarchical memory lives on disk; task-specific retrieval builds the working context. Nightly consolidation integrates new knowledge and corrections. Your agent accumulates institutional memory across projects and conversations.

Your project can outlive the agent working on it. Persistent task graphs, atomic checkpoints and independent supervision let a replacement worker resume the assignment. Completion is bound to current requirements and verified destination evidence.

Local compute makes persistent intelligence economical. Your CPU handles orchestration, state and integrity checks. Compiled context and reusable proofs reduce repeated inference, directing the model’s budget toward the difficult judgments that move work forward.

Open source. Native ChatGPT on your Mac. Built by Autonomous Production. Get AutoBot.

Benchmarks

AssistantBench

... continue reading

Explore topics: autobot osworld 2.0 assistantbench claude opus 5 max openai sol max