← 开源
astrio-labs

forall-mcp

Forall (∀) is a coding harness from Astrio that helps developers build correct software by generating spec-driven code alongside machine-checkable proofs.

AI EngineeringTest & guardPrompt & ScaffoldRust
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
576
Star
33
Fork
2
贡献者
创建于 2025-07-18 · 更新于 2026-10-13 · 今日第 16710 名
主要开发者
nolanlwinradleyle

astrio-labs/forall-mcp 排名第 16,710,有 576 个星标。

同类别比较

astrio-labs/forall-mcp 排名第 16,710,此处有 8 个同类条目;ZimoLiao/scholaraio 排名第 16,709。

同类别比较
名称排名指标
MoonshotAI/kimi-agent-sdk16,687
语言:
TypeScript
星标数:
577
分叉数:
88
简介:
Kimi Agent SDK provides a programmatic interface to interact with the Kimi CLI
levnikolaevich/claude-code-skills16,695
语言:
Shell
星标数:
577
分叉数:
87
简介:
Standalone skills for Claude Code and Codex: product discovery, architecture, implementation, technical foundations, reviews and delivery, with explicit scope and verification.
wallen0322/ComfyUI-Wan22FMLF16,702
语言:
Python
星标数:
577
分叉数:
30
简介:
An experimental node
ZimoLiao/scholaraio16,709
语言:
Python
星标数:
576
分叉数:
78
简介:
Scholar All-In-One: A research infrastructure for AI agents
resend/resend-mcp16,717
语言:
TypeScript
星标数:
576
分叉数:
90
简介:
The official MCP server to send emails and interact with Resend
v-modal/vmodal_sdk_android16,719
语言:
Kotlin
星标数:
576
分叉数:
12
简介:
Video Search SDK for Android Kotlin. Integrate in any video app
blorm-network/ZerePy16,729
语言:
Python
星标数:
575
分叉数:
252
简介:
ZerePy an open-source framework for AI agents written in Python
lartpang/SAMs-CDConcepts-Eval16,734
语言:
Python
星标数:
575
分叉数:
32
简介:
Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
关键参数与规格
关键参数与规格
参数值
语言Rust
类别AI Engineering
子类别Test & guard,Prompt & Scaffold
关键词Automated testing, DevOps, Spec-driven development
星标数576
分叉数33
贡献者2
创建日期2025-07-18
更新日期2026-10-13
1 天星标数0
排名16,710
上次排名16,498
排名变化-212
7 天星标排名19,229
上次 7 天星标排名19,200
7 天星标排名变化-29
总星标排名17,327
上次总星标排名17,297
总星标排名变化-30
README 摘录

Why Forall exists Review has always been the bottleneck in software. It is now the failure point, because code is produced faster than anyone can check it. Neither tells you whether the code does what it was supposed to do. Formal verification answers that question, as far as your specification states it, and it never failed on capability. Provers have been checking real programs for years. What kept them out of ordinary engineering was adoption cost. Writing the specifications, contracts

and invariants a prover needs was more tedious than writing the code itself. That is precisely the work language models are now good at. The barrier was labour, and labour just got cheap. Evidence can therefore become a build artifact rather than something reconstructed by hand long after the code is done. Standards such as IEC 62304 and DO-178C require traceability from each requirement to the verification that discharges it. Mission-critical code should carry that evidence the way

a paper carries its references, attached to the specific claim it supports. A green mark that lies is worse than no mark. A proof is only as strong as the contract it discharges, and property testing only samples. Those differences matter, so Forall reports four levels of evidence instead of a pass and a fail, grading every requirement by the strongest evidence a machine actually produced, never by what was claimed. Chat on your plan's hosted models, or bring your

own model API key (OpenAI, OpenRouter, Anthropic (Claude), Google Gemini, Azure OpenAI, or Claude via Amazon Bedrock). **Note:** A binary release must exist on GitHub Releases before install succeeds. Add to your MCP client: Your coding agent edits the workspace from verify reports. Supported programming languages Forall grades every requirement by the strongest evidence a machine actually produced for it. Statistical evidence, honestly ranked below a proof. We are expanding to more languages, and to filling in more of this

table for the languages already listed, based on demand. Opt out any time in : Connect Join our Discord and X communities. License This repository is licensed under the Apache-2.

常见问题

记录了多少星标和分叉?

astrio-labs/forall-mcp 有 576 个星标和 33 个分叉。

仓库排名是多少?

astrio-labs/forall-mcp 排名第 16,710。

记录的语言和类别是什么?

astrio-labs/forall-mcp 有 576 个星标,语言为 Rust,类别为 AI Engineering。

哪个仓库排名最接近?

astrio-labs/forall-mcp 与 ZimoLiao/scholaraio 比较,后者排名第 16,709,有 576 个星标。

README

Why Forall exists

Review has always been the bottleneck in software. It is now the failure point, because code is produced faster than anyone can check it. Tests sample a handful of inputs. Types constrain shape. Neither tells you whether the code does what it was supposed to do.

Formal verification answers that question, as far as your specification states it, and it never failed on capability. Provers have been checking real programs for years. What kept them out of ordinary engineering was adoption cost. Writing the specifications, contracts and invariants a prover needs was more tedious than writing the code itself. That is precisely the work language models are now good at. The barrier was labour, and labour just got cheap.

Evidence can therefore become a build artifact rather than something reconstructed by hand long after the code is done. Regulated work already depends on it. Standards such as IEC 62304 and DO-178C require traceability from each requirement to the verification that discharges it. Mission-critical code should carry that evidence the way a paper carries its references, attached to the specific claim it supports.

A green mark that lies is worse than no mark. A proof is only as strong as the contract it discharges, and property testing only samples. Those differences matter, so Forall reports four levels of evidence instead of a pass and a fail, grading every requirement by the strongest evidence a machine actually produced, never by what was claimed.

Two ways to use Forall

1. Install Forall CLI

Full coding agent — specs, proofs, and workflow in your terminal.

curl -fsSL https://forall.astrio.app/install.sh | bash
forall

Add ~/.local/bin to your PATH if needed, then run forall --version.

On first launch, sign in with your Forall account — your browser opens, no API key to paste. Chat on your plan's hosted models, or bring your own model API key (OpenAI, OpenRouter, Anthropic (Claude), Google Gemini, Azure OpenAI, or Claude via Amazon Bedrock). Then forall init in a git repo and start working.

Note: A binary release must exist on GitHub Releases before install succeeds.

2. MCP verify-only

Stay on Cursor, Claude Code, or any MCP client — add hosted verification via MCP. Do not install the CLI.

  1. Create an API key at forall.astrio.app/dashboard
  2. Add to your MCP client:
{
  "mcpServers": {
    "forall": {
      "command": "npx",
      "args": ["-y", "@astrio/forall-mcp"],
      "env": {
        "FORALL_API_KEY": "forall_..."
      }
    }
  }
}

Your coding agent edits the workspace from verify reports. See docs/getting-started.md and docs/hosted-mcp.md.

Supported programming languages

Forall grades every requirement by the strongest evidence a machine actually produced for it. Not every rung is reachable in every language, because the rung depends on the tool behind it:

Spec tracked Property tested Contracted Proved
TypeScript ✓ ✓ ✓ ✓
Python ✓ ✓ ✓ ✗
Rust ✓ ✗ ✓ ✓
Java ✓ ✗ ✓ ✓
C ✓ ✗ ✓ ✓
  • Spec tracked — a requirement cites this code.
  • Property tested — a generator ran over many inputs and found no counterexample. Statistical evidence, honestly ranked below a proof.
  • Contracted — a machine-checkable contract is written against the code, but nothing has confirmed it yet.
  • Proved — a prover discharged that contract's obligations.

We are expanding to more languages, and to filling in more of this table for the languages already listed, based on demand.

Telemetry

First-party builds send product usage analytics — feature and reliability events, never your code or prompts. Opt out any time in ~/.forall/config.toml:

[analytics]
enabled = false

Connect

Join our Discord and X communities.

License

This repository is licensed under the Apache-2.0 License.

排名相邻
同类项目