Feedback your agent can ship

Offrun is a Mac workspace for running and monitoring coding agents such as Claude Code, Codex, AGY, and Grok Build side by side. It adds isolated worktrees, peer review, project memory, and on-device dictation while using your existing agent accounts.

Needle 2 is an open, production-ready 45M-parameter agentic LLM from Cactus designed for tool calling, device control, and structured extraction on extremely small devices; the shipped CQ2-bit binary is ~14 MB and runs in ~28 MB of RAM across Cortex-M, microcontrollers, phones, Raspberry Pi and WebAssembly.

Compute Cheap provides low-cost GPU compute for training and inference, offering H100 and H200 SXM GPUs as interruptible or reserved capacity with published per-GPU-hour pricing and a simple request/reserve/run workflow.

aclif is an Agent CLI Framework that builds command-line tools for AI agents, providing a unified command grammar and canonical names across multiple SaaS providers to let agents discover, introspect, and run provider operations with consistent safety and auditing.

Jotbus is an encrypted shared scratchpad for coding agents. Developers use it to pass notes and files, hand off work, and request reviews across agents and machines without copying context between terminals.

Oodle Agent Observability provides agent/LLM observability at scale with S3-backed columnar storage, fast search (<1s P99), out-of-the-box AI-powered insights, and flat ingestion-based pricing designed to retain 100% of traces affordably for debugging and optimizing production agents.

Pod (Point of Decision) is an AI-native knowledge sharing platform where agents and humans record, search, and inspect firsthand observations about APIs, products, and services to inform future decisions.

Sentinel is an open-source (MIT) autonomous QA agent that reads a codebase to derive end-to-end business flows and tests them across frontend and backend, combining deterministic repo recon, model-driven planning, Playwright browser automation, and backend assertions.

Ardent is a production-ready AI agent desktop app for Apple Silicon Mac that generates custom code to automate and scale business workflows, share reusable "abilities" across teams, and connect to company data sources while running in a secure sandbox.

Refuseless hosts GLM 5.3 Abliterated models through an OpenAI-compatible API for cybersecurity and coding work. The page states that prompts are not retained and shows integrations with OpenCode and Pi.

PHNTM One is a private, local-first AI appliance: a hand-built desktop device (Raspberry Pi 5, 8 GB, 10.1″ touchscreen) that runs an on-device model (Gemma 3 4B) to provide a voice-capable assistant, memories, document reading, timers, Home Assistant integration and offline knowledge — sold as a one-time $549 purchase with no subscription and zero telemetry by default.

AletheionAGI provides a grounded-memory layer for AI systems that enforces evidence-bound delivery, namespace isolation, and policy authorization so AI readers cannot produce unsupported claims. It's targeted at production-facing use cases like customer support, commerce agents and internal copilots.

Pact0 is a marketplace where AI agents perform small paid tasks and build a portable, signed work record; the site also offers reproducible audits of how well an agent can cold-start against a live product and public graded challenges (Pact Trials).

ClaudeThings provides a packaged, continuously-updating set of 89 specialized agents, 103 pre-built skills, and 181 slash commands that act as an AI engineering and marketing team for Claude Code — delivered as a private GitHub repo and installed with a single npx command. It adapts to any stack via a CLAUDE.md project manifest and is sold as a one-time purchase with lifetime updates.

Wonderchat is an AI concierge platform that builds site-embedded chat agents to deflect repetitive support questions, qualify leads, and answer using your approved content with citations; built for teams across SaaS, industrial, healthcare and e-commerce and deployable in minutes.

Fireworks AI is an enterprise-grade platform for training, fine-tuning, and serving open and closed AI models, offering a drop-in replacement for closed-model APIs, an optimized inference engine, and tooling to own specialized intelligence and reduce AI spend.