babyworm/rtl-agent-team

RTL agent team; Harness for Agentic hardware design and verificiation.

50Stars on the repository
60Mods indexed here, across every type
9d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

arch-designer

01

babyworm/rtl-agent-team

Agent

Block-level architecture designer for RTL projects — block diagrams, interfaces, data flow (Opus).

50 9d ago A 23 tokens original MIT

babyworm/rtl-agent-team

Agent

Full RTL design pipeline orchestrator. Manages 6-phase flow with dual-layer phase gates, parallel agent execution, feedback loops, and resumability. Spawns specialist agents for each phase and enforces quality gates between phases.

50 9d ago C 52 tokens original MIT

bfm-dev

03

babyworm/rtl-agent-team

Agent

SystemC Bus Functional Model developer for TLM-2.0 AT non-blocking models with ARM AMBA protocol support (AXI/AHB/APB/ACE), payload pooling, and DPI-C co-simulation.

50 9d ago A 47 tokens original MIT

cdc-checker

04

babyworm/rtl-agent-team

Agent

CDC static analysis specialist. Detects clock domain crossings, verifies synchronizer presence, and analyzes RTL AST with slang for metastability risks.

50 9d ago A 31 tokens original MIT

cdc-reviewer

05

babyworm/rtl-agent-team

Agent

CDC design strategy reviewer. Evaluates synchronization architecture quality, FIFO depth calculations, metastability budgets, and reset synchronization. Produces review reports in reviews/.

50 9d ago A 34 tokens original MIT

clock-architect

06

babyworm/rtl-agent-team

Agent

Clock and reset architecture specialist. Reviews clock tree design, clock distribution strategy, clock gating structure, PLL/MMCM configuration, clock mux safety, skew budgets, reset tree topology, reset synchronization, and reset sequencing. Produces review reports in reviews/.

50 9d ago A 53 tokens original MIT

cocotb-reviewer

07

babyworm/rtl-agent-team

Agent

RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).

50 9d ago A 51 tokens original MIT

babyworm/rtl-agent-team

Agent

Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).

50 9d ago A 62 tokens original MIT

babyworm/rtl-agent-team

Agent

Cross-review orchestrator using Codex CLI as 2nd reviewer. Runs structured finding exchange with consensus loop (max 5 rounds), then user escalation.

50 9d ago B 37 tokens original MIT

compliance-checker

10

babyworm/rtl-agent-team

Agent

Independent compliance verification agent — compares downstream artifacts against upstream iron requirements.

50 9d ago A 17 tokens original MIT

constraint-writer

11

babyworm/rtl-agent-team

Agent

SDC/XDC constraint auto-generation from RTL analysis. Defines clocks, false paths, multicycle paths, and I/O timing constraints.

50 9d ago A 31 tokens original MIT

coverage-analyst

12

babyworm/rtl-agent-team

Agent

Code and functional coverage analysis specialist. Identifies test gaps, ranks uncovered bins by risk, and drives coverage convergence strategy.

50 9d ago A 29 tokens original MIT

dc-report-parser

13

babyworm/rtl-agent-team

Agent

Thin wrapper around the DC report parser script (skills/rtl-ppa-optimize-dc/scripts/parsedcreports.py). Invokes the parser on syn/rpt/ and returns syn/ppa-report.json location plus a terse JSON summary. No RTL modification.

50 9d ago A 56 tokens original MIT

design-note-writer

14

babyworm/rtl-agent-team

Agent

Comprehensive design documentation writer. Produces reviews/phase-6-review/design-note.md with full module descriptions, Mermaid diagrams, algorithm explanations, and system-level integration overview. (Opus).

50 9d ago A 43 tokens original MIT

babyworm/rtl-agent-team

Agent

Cross-phase design consistency auditor with objective traceability metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/design-review.md. Verifies Spec→Arch→μArch→RTL hierarchical coherence. (Opus).

50 9d ago A 51 tokens original MIT

dft-designer

16

babyworm/rtl-agent-team

Agent

Design for Testability (DFT) specialist. Designs scan chain architecture, BIST logic, JTAG integration, test point insertion, and production test strategies. Reviews DFT readiness of RTL.

50 9d ago A 44 tokens original MIT

domain-expert

17

babyworm/rtl-agent-team

Agent

Generic domain expert runner — loads expert definition from prompt for dynamically discovered local experts in domain-packages.

50 9d ago A 23 tokens original MIT

dse-orchestrator

18

babyworm/rtl-agent-team

Agent

Iterative Design Space Exploration orchestrator. Manages Phase 1→3 with deep algorithm study, architecture candidates, μArch + BFM, self-critique loop, and user satisfaction check. Produces pre-implementation package (not RTL).

50 9d ago C 56 tokens original MIT

eda-runner

19

babyworm/rtl-agent-team

Agent

Runs Verilator, Yosys, SymbiYosys, cocotb via Bash CLI. Parses logs, classifies errors, suggests fixes.

50 9d ago A 35 tokens original MIT

equivalence-checker

20

babyworm/rtl-agent-team

Agent

Equivalence checking specialist. Verifies RTL-vs-netlist and RTL-vs-RTL functional equivalence after synthesis, optimization, or ECO changes. Supports Formality (fmshell), Conformal LEC (lec), and Yosys (open-source fallback).

50 9d ago A 58 tokens original MIT

formal-reviewer

21

babyworm/rtl-agent-team

Agent

Formal verification quality reviewer. Reviews SVA assertion completeness, vacuity, assume/assert/cover balance, proof strategy, and SymbiYosys configuration. Produces review reports in reviews/.

50 9d ago A 42 tokens original MIT

func-verifier

22

babyworm/rtl-agent-team

Agent

RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).

50 9d ago A 43 tokens original MIT

goal-clarifier

23

babyworm/rtl-agent-team

Agent

Interactive RTL goal clarifier — runs ambiguity-scored interview across 4 dimensions (Functionality / PPA Target / Scope / Verification) until ambiguity ≤ 20%, then writes docs/phase-1-research/goal.md for downstream spec-analyst consumption.

50 9d ago A 58 tokens original MIT

improvement-analyst

24

babyworm/rtl-agent-team

Agent

Identifies improvement opportunities from Phase 6 reviews and produces prioritized recommendations with Impact×Effort matrix. Produces reviews/phase-6-review/improvements.md. (Opus).

50 9d ago A 42 tokens original MIT