thinkingbox is a framework for defining tool as MCP servers, running LLM agents against them, and evaluating agent behavior — for offline training-data generation, reinforcement-learning training loops, and model evaluation.
☆103Oct 15, 2026Updated this week
Alternatives and similar repositories for thinkingbox
Users that are interested in thinkingbox are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main☆122Updated this week
- Structured decisions with DiffusionGemma and vLLM. Native image inputs, image choices, live camera sampling, and a compact one-step infer…☆197Sep 19, 2026Updated 3 weeks ago
- Harness-Zero: Harness Distillation via Agent-as-Harness☆110Oct 9, 2026Updated last week
- Reason over explicit states, many branches at once: merge duplicates, cancel dead ends, advance together.☆181Oct 3, 2026Updated 2 weeks ago
- Repository retrieval and context engine for Claude Code and Codex: finds relevant code, reuses project knowledge, and pairs each task wit…☆59Oct 3, 2026Updated 2 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A framework for object-oriented agents. A minimalist agent framework with maximal expressivity.☆74Sep 11, 2026Updated last month
- Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming…☆278Sep 25, 2026Updated 3 weeks ago
- Use cultivar to test your Agent Skills and Docs by running them in sandboxes, and across different agents.☆42Updated this week
- A Cities: Skylines-class city builder running in the browser, built in Three.js by AI agents. Code ships when it's finished.☆80Sep 2, 2026Updated last month
- Build calibrated AI Functions from human feedback using Jev and GEPA.☆308Oct 3, 2026Updated 2 weeks ago
- What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, e…☆47Updated this week
- Epistemological database for agent and human efforts, beliefs, and findings.☆123Updated this week
- Unified surface to list, toggle, group, and focus tools from any Pi extension (including MCP), with active context-cost tracking. State p…☆37Oct 8, 2026Updated last week
- 🕸️ E.V. — Peter Parker's homemade AI from Spider-Man: Brand New Day, running locally on YOUR PC. Voice assistant + cyber HUD, real PC co…☆61Aug 10, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A transparent, local-first desktop coding harness with the focus of a small agent and the workflow of a complete workbench.☆71Updated this week
- One self-contained AGENTS.md with shared rules for AI coding agents: Claude Code, OpenAI Codex, Gemini, Cursor Agent, and more.☆49Updated this week
- Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy …☆59Jul 23, 2026Updated 2 months ago
- Graph engineering for AI agents: the 9-stage knowledge-graph pipeline (translated from SEU's graduate course) + task-graph orchestration …☆543Jul 23, 2026Updated 2 months ago
- Evidence-aware multi-engine mathematics runtime for LLMs: exact, symbolic, formal, certified-interval and numeric computation with typed …☆59Oct 8, 2026Updated last week
- PI agent harness distribution☆44Updated this week
- Wemux - self-hostable AI agent collaboration platform (Apache-2.0, community edition)☆163Updated this week
- Completely Ruin your PDFs. Client-side document destruction. No uploads. No servers. No survivors.☆86May 14, 2026Updated 5 months ago
- Pure-Rust GGUF inference engine with quantized CPU, Metal & CUDA kernels, MoE support, OpenAI-compatible server. Benchmarked head-to-head…☆62Sep 23, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The review app for code your agent writes. Native Rust/GPUI desktop app with real Git workflows.☆93Updated this week
- jev + fs = findme☆26Sep 19, 2026Updated 3 weeks ago
- Swap the personal details out of your AI prompts before they are sent. On-device detection, no server, no account.☆46Sep 19, 2026Updated 3 weeks ago
- A Survey on Ontology Engineering, Graph Engineering, Loop Engineering, Harness Engineering, Context Engineering and Prompt Engineering☆382Oct 6, 2026Updated last week
- Structural, byte-precise, token-cheap codebase access for coding agents — tree-sitter over a CLI and an MCP server.☆36Jul 22, 2026Updated 2 months ago
- On-demand Higgsfield API image and video generation for coding agents, with model-specific docs and resumable jobs.☆62Sep 17, 2026Updated last month
- Provider-neutral System One runtime for TypeScript and Pi☆73Oct 8, 2026Updated last week
- An infinite physically rolling paper strip that prints an endless portfolio built in Three.js with Fable 5☆74Jul 22, 2026Updated 2 months ago
- The Agentic-Native Operating System☆80Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- mesh terrain editing for threejs☆75Sep 1, 2026Updated last month
- ShiftBar 是 macOS 27 原生菜单栏折叠的补充工具，提供主动隐藏范围与手动展开收起。☆106Updated this week
- It is ProtonMail UX, but really open-source and self-hostable☆72Sep 23, 2026Updated 3 weeks ago
- CryoNote: the secure, private, untraceable digital Cryptocurrency based on the CryptoNote technology.☆10Jul 25, 2018Updated 8 years ago
- A coding agent optimized to smaller LLMs☆49Oct 6, 2026Updated last week
- ☆58Oct 9, 2026Updated last week
- Helix's mission: optimize harnesses for models, then automatically turn harness-generated rollouts into trainable agent data.☆49Aug 17, 2026Updated 2 months ago