spec-driven repositories
Trending repositories tagged spec-driven, ranked by trending score. Updated daily.
-
1
github/spec-kit
💫 Toolkit to help you get started with SDD or any other process!
GitHub · Python · 150,757 stars · 13,545 forks · +410 stars in 24 hours · Trending score 4.92
-
2
JetBrains/thinkrail
ThinkRail is the agentic IDE that gets better every time you use it
GitHub · TypeScript · 8,369 stars · 532 forks · +33 stars in 24 hours · Trending score 3.12
-
3
wellwelwel/lagune
🪼 Lagune AI is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).
GitHub · TypeScript · 222 stars · 8 forks · +6 stars in 24 hours · Trending score 1.84
-
4
Looted/kibi
Kibi is a requirement-conformance layer for AI coding agents that keeps product intent connected to code and tests, and catches when implementations drift from it.
GitHub · TypeScript · 13 stars · 3 forks · +1 stars in 24 hours · Trending score 0.73
-
5
DraconDev/pi-goal-list-loop-audit
Long-running autonomy for Pi: draft goals, build projects from specs, run audited task queues, and recover interrupted work. Independent auditors verify completion.
GitHub · TypeScript · 29 stars · 16 forks · 0 stars in 24 hours · Trending score 0.23
-
6
lindoelio/spec-driven-steroids
Spec-Driven Steroids is a very simple toolkit designed to bring discipline to AI-powered software engineering. It injects high-standard workflows (SDD) directly into the native environments of your favorite AI tools.
GitHub · Go · 55 stars · 2 forks · 0 stars in 24 hours · Trending score 0.22
-
7
emgiezet/aisdlc
AI SDLC harness for Claude Code — spec-driven delivery for agents: task router, dense test floors, automated QA, and a fire-and-forget queue that turns approved specs into reviewable pull requests
GitHub · Shell · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.09
-
8
traverse-framework/traverse
Contract-driven runtime for portable business capabilities — spec-governed, WASM-first, composable across browser, edge, cloud, and AI.
GitHub · Rust · 78 stars · 6 forks · −5 stars in 24 hours · Trending score 0.09
-
9
compforge/case-code-review
A trajectory-evaluation-driven agentic code review pipeline that turns code changes into evidence-backed Findings.
GitHub · Go · 8 stars · 2 forks · 0 stars in 24 hours · Trending score 0.07
-
10
btspoony/mstar-harness
An omni-plugin for harness engineering workflows with multi-agents, programmatic gates and skills.
GitHub · TypeScript · 72 stars · 5 forks · 0 stars in 24 hours · Trending score 0.06
-
11
specd-sdd/SpecD
Spec-driven development for humans and AI agents. Define, verify, and evolve behavioral specifications across single repos, monorepos, and multi-repo systems.
GitHub · TypeScript · 20 stars · 2 forks · 0 stars in 24 hours · Trending score 0.05
-
12
sengac/fspec
FSPEC: The Spec-Driven, Multi-Agent Harness. It is infrastructure for the "Dark Factory" - the emerging model of fully autonomous software development where AI agents handle all implementation while humans focus on defining what to build and why.
GitHub · Rust · 103 stars · 7 forks · 0 stars in 24 hours · Trending score 0.02
-
13
kivo360/OmoiOS
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolated sandboxes, DAG dependencies. Open-source, self-hostable, model-agnostic (Claude / Gemini / Codex).
GitHub · Python · 80 stars · 7 forks · 0 stars in 24 hours · Trending score 0.00
-
14
attilaszasz/sdd-pilot
Replace chaotic AI code generation with a disciplined, spec-driven workflow. SDD Pilot enforces structured development phases and quality gates, leveraging AI agents to conduct online research for best practices and plan your architecture before a single line of code is written.
GitHub · JavaScript · 98 stars · 10 forks · 0 stars in 24 hours · Trending score 0.00
-
15
hoplogic/hop3
HOP 3.0 — HopSpec task-spec language + HopJIT execution engine for LLM agents
GitHub · TypeScript · 22 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
16
HuginnIndustries/CodeCartographer
Evidence-backed reverse engineering and human-gated software planning for Pi and MCP coding agents.
GitHub · JavaScript · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
17
Tyrantwa70342ve/garage-resp
Six-skill spec-driven engineering pod for Claude Code — scaffold specs, research, discover direction, generate design variants, implement, and visually verify, with hard handoffs that prevent silent assumptions
GitHub · 25 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
18
rusharlabs/house-party-protocol
A local harness that orchestrates agent teams on Claude Code and Codex CLI and counts as done only what they prove: waves and lanes split the work, another model family reviews it, councils keep the dissent that lost, typed decisions with Jev are measured before they are trusted, and approvals bind to the bytes they approved. No model calls.
GitHub · Python · 5 stars · 6 forks · 0 stars in 24 hours · Trending score 0.00