Open Source Ecosystem

The Agentic Coding FlywheelTL;DR EditionTL;DR Edition

16 core tools and 13 supporting utilities that transform multi-agent AI coding workflows. Each tool makes the others more powerful - the more you use it, the faster it spins. While others argue about agentic coding, we're just over here building as fast as we can.

29
Ecosystem Tools
3,600+
GitHub Stars
5
Languages
Scroll to explore

Why a Flywheel?

A flywheel stores rotational energy - the more you spin it, the easier each push becomes. These tools work the same way. The more you use them, the more valuable the system becomes.

Every agent session generates searchable history (CASS). Past solutions become retrievable memory (CM). Dependencies surface bottlenecks (BV). Agents coordinate without conflicts (Mail). Each piece feeds the others.

The result: I shipped 20,000+ lines of production Go code in a single day with BV. The flywheel keeps spinning faster - my GitHub commits accelerate each week because each tool amplifies the others.

Flywheel16 Core ToolsMailBVCASSUBSCMNTMBRACFSDCGRUSLBMSRCHCAAMWABrenner

Hover over tools to see connections

/

Core Flywheel Tools

16

The backbone of multi-agent development: session management, communication, task tracking, static analysis, memory, search, safety guards, multi-repo sync, and automated setup. These tools form a self-reinforcing loop where each makes the others more powerful.

Mail

Core

MCP Agent Mail

1.4K

A mail-like coordination layer for multi-agent workflows. Agents send messages, read threads, and reserve files asynchronously via MCP tools - like Gmail for AI coding agents. HTTP-only FastMCP transport with static export.

Why It's Useful

Critical for multi-agent setups. When 5+ Claude Code instances work the same codebase, they need to coordinate who's editing what. Agent Mail prevents merge conflicts via advisory file reservations with pre-commit guard enforcement, and builds an audit trail of all agent decisions via SQLite + Git dual persistence.

Key Features

  • Threaded messaging between AI agents
  • Advisory file reservations
  • SQLite-backed persistent storage
  • MCP integration for any compatible agent

Tech Stack

PythonFastMCPFastAPISQLite

Synergies

BVTask IDs in mail threads link to Beads issues
CMShared context persists across agent sessions via CM
SLBTwo-person approval requests delivered via agent inboxes
NTMNTM-spawned agents auto-register with Agent Mail

BV

Core

Beads Viewer

891

A fast terminal UI for viewing and analyzing Beads issues. Applies graph theory (PageRank, betweenness centrality, critical path) to identify which tasks unblock the most other work.

Why It's Useful

Issue tracking is really a dependency graph. BV lets Claude prioritize beads intelligently by computing actual bottlenecks. The --robot-insights flag gives PageRank rankings for what to tackle first.

Key Features

  • PageRank-based issue prioritization
  • Critical path analysis
  • Robot mode for AI agent integration
  • Interactive TUI with vim keybindings

Tech Stack

GoBubble TeaLip GlossGraph algorithms

Synergies

BRReads and visualizes issues from beads_rust (.beads/*.jsonl)
MailTask updates trigger notifications via Agent Mail
UBSBug scanner findings become blocking issues
CASSSearch prior sessions for task context
NTMNTM uses --robot-plan for dependency analysis during multi-agent orchestration

BR

Core

beads_rust

128

Local-first issue tracking for AI agents. SQLite for fast local queries, JSONL export for git-friendly collaboration. Full dependency graph with blocking/blocked-by relationships, priorities P0-P4.

Why It's Useful

Your issues travel with your repo - no external service required. Non-invasive design: never runs git commands automatically. Agents can create, update, and close issues with simple CLI commands. The bd alias provides backward compatibility.

Key Features

  • Local-first issue storage
  • Dependency graph tracking
  • Labels, priorities, comments
  • JSON output for agents

Tech Stack

RustSerdeJSONL

Synergies

BVBV visualizes and analyzes issues created by br
MailTask updates notify agents via mail
NTMNTM spawns agents that pick work from beads
UBSUBS --beads-jsonl outputs findings as importable beads

CASS

Core

Coding Agent Session Search

307

Blazing-fast search across all your past AI coding agent sessions. Indexes 11 agent formats: Claude Code, Codex, Cursor, Gemini, ChatGPT, Cline, Aider, Pi-Agent, Factory, OpenCode, Amp. Sub-60ms queries with optional semantic search.

Why It's Useful

You've solved this problem before - but which session? CASS lets you search 'how did I fix that React hydration error' and instantly find the exact conversation. Three search modes (lexical, semantic, hybrid), HTML export with encryption, and multi-machine sync via SSH.

Key Features

  • Unified search across all agent types
  • Sub-second search over millions of messages
  • Robot mode for AI agent integration
  • TUI for interactive exploration

Tech Stack

RustTantivyRatatuiJSONL parsing

Synergies

CMIndexes memories stored by CM for retrieval
NTMSearches all managed agent session histories
BVLinks search results to related Beads tasks

ACFS

Core

Flywheel Setup

234

One-command bootstrap that transforms a fresh Ubuntu VPS into a fully-configured agentic coding environment. CLI provides doctor (47+ health checks), update (category-specific), cheatsheet (50+ aliases), and session management.

Why It's Useful

Setting up a new development environment takes hours. ACFS does it in 30 minutes, installing 30+ tools, three AI agents, and all flywheel tooling. Post-install CLI provides `acfs doctor` for health checks and `acfs update` for maintenance.

Key Features

  • acfs doctor: 47+ health checks across 7 categories
  • acfs doctor --deep: Functional tests (auth, DB connectivity)
  • acfs update: Category-specific with --dry-run preview
  • acfs cheatsheet: 50+ aliases for modern CLI tools
  • acfs dashboard: Static HTML dashboard generation
  • Update logging to ~/.acfs/logs/updates/

Tech Stack

BashYAML manifestNext.js wizard

Synergies

NTMInstalls and configures NTM
MailSets up Agent Mail MCP server
DCGInstalls DCG safety hooks

UBS

Core

Ultimate Bug Scanner

132

A meta-runner that fans out per-language scanners across 8 languages (JS/TS, Python, Go, Rust, C/C++, Java, Ruby, Swift). Uses ast-grep for AST-based pattern matching with 18 detection categories and 1000+ bug patterns.

Why It's Useful

AI coding agents move 10-100x faster than humans. UBS keeps pace with sub-5-second scans and auto-wires guardrails into Claude Code, Codex, Cursor, Gemini, and Windsurf agents. The --beads-jsonl output creates Beads issues directly from findings.

Key Features

  • 1000+ built-in detection patterns
  • Consistent JSON output format
  • Multi-language support
  • Perfect for pre-commit hooks

Tech Stack

BashPattern matchingJSON output

Synergies

BVBug findings become blocking issues via --beads-jsonl
BRDirect JSONL output for beads_rust issue tracking

DCG

Core

Destructive Command Guard

89

Claude Code PreToolUse hook that blocks dangerous commands BEFORE execution. 50+ packs across 17 categories: git (reset --hard, force push), filesystem (rm -rf), databases (DROP TABLE), Kubernetes, cloud providers, and more.

Why It's Useful

AI agents can and will run 'rm -rf /' if they think it solves your problem. DCG catches catastrophic commands before they execute with sub-millisecond latency. Safe directory exceptions (/tmp, /var/tmp, $TMPDIR) allow temp operations without friction.

Key Features

  • Intercepts rm -rf, git reset --hard, etc.
  • SIMD-accelerated pattern matching
  • Configurable allowlists
  • Command audit logging

Tech Stack

RustSIMDShell integration

Synergies

SLBWorks alongside SLB for layered command safety
NTMGuards all commands in NTM-managed sessions

RU

Core

Repo Updater

67

Multi-repo management system: sync 100+ repos, AI-assisted code review with priority scoring, dependency updates across package managers, and agent-driven commit automation.

Why It's Useful

Managing 100+ repos manually is impossible. 'ru sync' handles clone/pull in parallel. 'ru review' discovers issues/PRs via GraphQL batch queries, scores by priority (security+50, bugs+30, age), and spawns isolated Claude Code sessions in worktrees.

Key Features

  • One-command multi-repo sync
  • Parallel operations
  • Conflict detection with resolution hints
  • AI code review integration

Tech Stack

BashGit plumbingGitHub CLI

Synergies

NTMUses ntm robot mode API for AI review session management
MailCoordinates repo claims across parallel agents
BVMulti-repo task tracking via beads integration

CM

Core

CASS Memory System

152

Cross-agent procedural memory system. Transforms scattered sessions from all your AI agents into persistent, unified knowledge. Three-layer cognitive architecture: Episodic (raw sessions via CASS) → Working (diary summaries) → Procedural (playbook rules with confidence tracking).

Why It's Useful

A debugging technique discovered in Cursor is immediately available to Claude Code. Rules have 90-day decay half-life and 4× harmful weight for mistakes. Bad rules auto-invert into anti-pattern warnings. Every agent learns from every other agent's experience.

Key Features

  • Three memory layers: episodic, working, procedural
  • MCP integration for any compatible agent
  • Automatic memory consolidation
  • Cross-session context persistence

Tech Stack

TypeScriptBunMCP ProtocolSQLite

Synergies

CASSPrimary dependency - provides episodic memory via session search
MailMemory context shared across agent conversations
BVTask patterns and successful approaches remembered

NTM

Core

Named Tmux Manager

69

A multi-agent tmux orchestration tool with 80+ commands. Spawns Claude, Codex, and Gemini agents in named panes with type classification (cc/cod/gmi). Monitors context windows, detects file conflicts, and provides robot mode for automation.

Why It's Useful

Running multiple AI agents simultaneously creates chaos without orchestration. NTM provides the command center: spawn agents with one command, broadcast prompts to specific types, monitor context usage, and coordinate via Agent Mail. Sessions persist across SSH disconnects and system reboots.

Key Features

  • Named agent panes with type classification
  • Broadcast prompts to agent types
  • Session persistence across reboots
  • Dashboard view of active agents

Tech Stack

GoBubble Teatmux

Synergies

SLBSLB provides two-person rule safety checks for dangerous commands in NTM sessions
MailAgents auto-register with Mail; ntm mail commands for messaging; pre-commit guard enforces file reservations
CASSDirect integration via --robot-cass-search and --robot-cass-context commands
BVGraph analysis via --robot-plan and --robot-graph for dependency insights
BRBead management via --robot-bead-* commands for issue tracking

SLB

Core

Simultaneous Launch Button

49

Nuclear-launch-style two-person rule for dangerous commands. Four risk tiers classify commands via 40+ regex patterns: CRITICAL (2+ approvals), DANGEROUS (1 approval), CAUTION (30s auto-approve), SAFE (skip). Cryptographic signing, rollback support, and outcome analytics.

Why It's Useful

AI agents can and will run destructive commands if they think it solves your problem. SLB intercepts commands like 'rm -rf /', 'DROP DATABASE', and 'terraform destroy' requiring explicit approval from another agent or human reviewer before execution. Watch mode lets reviewing agents stream pending requests.

Key Features

  • Two-person rule enforcement
  • Command queue with approval workflow
  • Pattern-based risk detection
  • SQLite persistence

Tech Stack

GoBubble TeaSQLite

Synergies

DCGDCG blocks pre-execution, SLB validates with multi-agent approval
NTMCoordinates approval quorum across NTM-managed agents
MailApproval requests can be routed via Agent Mail
CAAMAccount switching can require SLB approval for team workflows

MS

Core

Meta Skill

10

Local-first skill management platform: dual persistence (SQLite + Git), hybrid search (BM25 + semantic + RRF), UCB bandit optimization, multi-layer security (ACIP + DCG), graph analysis via bv, MCP server for AI agents.

Why It's Useful

AI agents need reusable context to be effective. MS doesn't just store skills—it learns which ones work via UCB bandit optimization. Context-aware auto-loading suggests skills based on project type. Pack contracts optimize token budgets. The MCP server makes skills native tools for any AI agent.

Key Features

  • MCP server for native AI agent integration
  • Thompson sampling optimizes suggestions
  • Multi-layer security
  • Hybrid search with RRF

Tech Stack

RustSQLiteTantivyMCP

Synergies

CASSOne input source for skill extraction (not the only one)
CMSkills and CM memories are complementary knowledge layers
BVGraph analysis via bv for PageRank, bottlenecks, cycles
JFPJFP downloads remote prompts, MS manages local skills

RCH

Core

Remote Compilation Helper

35

Claude Code PreToolUse hook that offloads Rust compilation to remote workers. Intercepts cargo commands, syncs source via rsync + zstd, compiles on server-grade hardware, streams artifacts back.

Why It's Useful

Multi-agent swarms trigger many concurrent builds. RCH intercepts commands before execution and routes them to remote workers with health probes and priority scheduling. Agent detection coordinates builds across Claude Code, Codex, and Gemini sessions.

Key Features

  • Transparent cargo interception
  • Multi-worker pool with priority scheduling
  • Incremental artifact sync
  • Daemon mode with status monitoring

Tech Stack

RustrsynczstdSSH

Synergies

NTMAgents in NTM sessions use RCH for builds
RURU syncs repos that RCH then builds remotely
BVBuild tasks can be tracked via beads

CAAM

Core

Coding Agent Account Manager

45

Manages multiple accounts for Claude Code, Codex CLI, and Gemini CLI with sub-100ms switching. Vault profiles store auth files for instant activation without browser flows. Smart rotation algorithms automatically select the best profile based on cooldown state, health, and usage patterns.

Why It's Useful

When running multiple agents, you'll hit rate limits. CAAM lets you switch accounts instantly - no browser login, no waiting. Profile isolation enables parallel sessions where each agent uses its own credentials. Health scoring (🟢/🟡/🔴) shows which profiles are ready vs. cooling down.

Key Features

  • Sub-100ms account switching
  • Multi-provider support
  • Automatic key rotation
  • Session state preservation

Tech Stack

TypeScriptBunKeychain

Synergies

NTMNTM spawns agents with isolated CAAM profiles for parallel sessions
MailAccount switches can trigger Agent Mail notifications
SLBTeam approval workflows for account switching

WA

Core

WezTerm Automata

42

Terminal hypervisor that captures pane output in real-time, detects agent state transitions through pattern matching, and enables event-driven automation across multiple AI coding agents.

Why It's Useful

When running multiple AI agents in WezTerm, you need to know when they hit rate limits, complete tasks, or need approval. WA observes all panes with sub-50ms latency and triggers automated responses.

Key Features

  • Real-time terminal observation
  • Intelligent pattern detection
  • Robot Mode JSON API
  • Event-driven automation

Tech Stack

RustWezTerm APISQLite FTS5

Synergies

NTMWA observes agents spawned by NTM
MailState changes trigger Agent Mail notifications
BVTask completions can update bead status

Brenner

Core

Brenner Bot

28

Multi-agent scientific research orchestration platform based on Sydney Brenner's methodology. Manages full research artifact lifecycle: hypotheses, discriminative tests, anomalies, critiques, and evidence packs with cockpit runtime for parallel agent sessions.

Why It's Useful

Transforms AI agents into a collaborative research group with rigorous scientific discipline. The Brenner approach emphasizes exclusion over accumulation, third-alternative thinking, and discriminative experiments that collapse hypothesis space fast.

Key Features

  • Primary source corpus with citations
  • Multi-agent research sessions
  • Discriminative test ranking
  • Adversarial critique generation

Tech Stack

TypeScriptBunAgent MailMulti-model AI

Synergies

MailResearch sessions coordinate via Agent Mail threads with acknowledgment tracking
NTMCockpit runtime spawns parallel research agents with role-specific prompts
CASSResearch session history searchable for prior solutions and patterns

Supporting Tools

13

Extend the ecosystem with GitHub issue sync, archive search, and prompt crafting utilities. These tools enhance the core flywheel for specialized workflows.

GIIL

Get Image from Internet Link

24

Downloads full-resolution images from iCloud, Dropbox, Google Photos, and Google Drive share links using a four-tier capture strategy with headless Chromium automation.

Why It's Useful

When debugging remotely, users share cloud links but you're SSH'd into a headless server. GIIL's four-tier capture (download button → CDN interception → element screenshot → viewport fallback) ensures maximum quality retrieval for AI agent analysis.

Key Features

  • iCloud share link support
  • CLI-based image download
  • No browser required
  • Works over SSH

Tech Stack

BashcurliCloud API

Synergies

MailDownloaded images can be referenced in Agent Mail
CASSImage analysis sessions are searchable

SRPS

System Resource Protection Script

50

Installs ananicy-cpp with curated rules to auto-deprioritize background processes. Includes sysmoni Go TUI (Bubble Tea) with IO throughput, FD counts, per-core sparklines, JSON export. Works on Linux and WSL2.

Why It's Useful

When running cargo build, npm install, or multiple AI agents, SRPS prevents unresponsive systems by lowering priority of known resource hogs. Safety-first: no automated process killing. Helper tools for diagnostics.

Key Features

  • Automatic process deprioritization
  • Real-time TUI monitoring
  • 1700+ pre-configured rules
  • Custom rule creation

Tech Stack

GoC++ananicy-cppsystemd

Synergies

NTMKeeps tmux sessions responsive during heavy workloads
SLBPrevents multiple agents from starving each other for resources
DCGCombined safety: resource protection + command protection
PTPT identifies stuck processes, SRPS deprioritizes resource hogs

XF

X Archive Search

156

Ultra-fast search over X/Twitter data archives with sub-millisecond latency. Uses hybrid BM25 + semantic search with Reciprocal Rank Fusion. Indexes tweets, likes, DMs, and Grok conversations.

Why It's Useful

Your X archive is a goldmine of bookmarks, threads, and ideas, but Twitter's search is terrible. XF makes your archive instantly searchable (<10ms) with both keyword and semantic matching. DM context search shows full conversation threads.

Key Features

  • Sub-second search over large archives
  • Semantic + keyword hybrid search
  • No external API dependencies
  • Privacy-preserving local processing

Tech Stack

RustTantivyHash embeddingsRRF

Synergies

CASSSimilar search architecture and patterns
CMFound tweets can become memories

S2P

Source to Prompt TUI

78

World-class terminal UI for combining source code files into LLM-ready prompts. Tree explorer with vim-style navigation, live syntax preview, token counting, and structured XML-like output optimized for AI parsing.

Why It's Useful

Crafting prompts with code context is tedious and error-prone. S2P provides visual file selection with sizes and line counts, real-time token/cost estimation, quick file-type shortcuts (1-9,0,r), and produces structured output that LLMs parse reliably.

Key Features

  • Interactive file selection
  • Real-time token counting
  • Clipboard integration
  • Gitignore-aware filtering

Tech Stack

TypeScriptBunReactInktiktoken

Synergies

CASSGenerated prompts become searchable session history
CMEffective prompt patterns stored as procedural memories

APR

Automated Plan Reviser Pro

85

Iterative specification refinement via GPT Pro 5.2 Extended Reasoning + Oracle. Document bundling (README + spec + impl), convergence analytics with weighted scoring, session management, and robot mode JSON API for coding agents.

Why It's Useful

Complex specs need 15-20 review cycles. APR automates the loop: rounds 1-3 fix architecture, 4-7 refine interfaces, 8-12 handle edge cases, 13+ polish abstractions. Convergence score (≥0.75 = stable) tells you when to stop.

Key Features

  • Automated multi-pass refinement
  • Extended AI reasoning integration
  • Markdown-based plan processing
  • Progressive structure improvement

Tech Stack

BashOracle CLIGPT ProMarkdown

Synergies

JFPBattle-tested prompts can be refined into specifications
CMRefined plans become searchable memories
BVRefined specs generate well-structured beads

JFP

JeffreysPrompts CLI

120

Official CLI for jeffreysprompts.com - browse, search, and install battle-tested prompts as Claude Code skills. Features interactive fzf-style picker and task-based suggestion engine.

Why It's Useful

Instead of writing prompts from scratch, install proven patterns. The interactive mode (jfp i) lets you fuzzy-search the entire library, while jfp suggest recommends prompts based on your task description. Premium features include collections, cross-machine sync, and a skills marketplace.

Key Features

  • One-command skill installation
  • Browsable prompt categories
  • Claude Code skills integration
  • MCP server for agent access

Tech Stack

TypeScriptBunClaude Code Skills API

Synergies

MSJFP downloads remote prompts, MS manages local skills - they complement each other
APRDownloaded prompts can be refined into comprehensive specs via APR
CMEffective prompts become retrievable memories

PT

Process Triage

45

Bayesian-inference zombie/abandoned process detection using four-state classification (Useful, Useful-but-bad, Abandoned, Zombie) with evidence-based posterior probability scoring.

Why It's Useful

When builds hang or test runners go rogue, PT computes P(state|evidence) using process type, age, CPU/IO activity, memory, and past decisions. Confidence levels (very_high >0.99 to low <0.80) guide safe termination with identity validation and staged kill signals.

Key Features

  • Intelligent process scoring
  • Interactive TUI selection
  • Robot mode for automation
  • Resource usage analysis

Tech Stack

RustBayesian inferenceprocfs

Synergies

SRPSPT terminates stuck processes, SRPS prevents them from hogging resources
NTMClean up runaway processes in tmux sessions

TRU

TOON Rust

32

Token-optimized notation format for efficient LLM context packing. Compresses structured data into a dense format that maximizes information per token.

Why It's Useful

LLM context windows are precious. TRU compresses JSON, YAML, and other structured data into a compact notation that conveys the same information in fewer tokens, letting you fit more context into each request.

Key Features

  • Token-optimized notation format
  • Structured data compression
  • Multiple format support
  • Fast Rust implementation

Tech Stack

RustSerdeToken optimization

Synergies

S2PCompress source prompts for maximum context efficiency
CASSCompact session data for storage and search

RustProxy

Rust Proxy

18

Transparent HTTP/HTTPS proxy for debugging and inspecting network traffic. Routes requests through a local proxy for analysis.

Why It's Useful

When debugging API integrations or AI agent network calls, you need visibility into what's being sent and received. Rust Proxy provides transparent interception without modifying your code.

Key Features

  • Transparent HTTP/HTTPS proxy
  • Request/response inspection
  • Certificate generation
  • Low latency overhead

Tech Stack

RustTokioTLSHTTP proxy

Synergies

RANOComplementary network debugging - proxy vs observer
CASSLog network calls alongside session history

RANO

RANO

25

Network observer for AI CLI tools that logs requests and responses without proxying. Passive monitoring of LLM API traffic.

Why It's Useful

Understanding what your AI agents are actually sending to APIs helps with debugging, cost tracking, and optimization. RANO passively observes network traffic without adding proxy overhead.

Key Features

  • Passive network observation
  • LLM API traffic parsing
  • Request/response logging
  • Zero proxy overhead

Tech Stack

RustpcapNetwork monitoring

Synergies

CAUTNetwork observations feed usage tracking
CASSCorrelate network calls with session history

MDWB

Markdown Web Browser

42

Converts websites to clean Markdown for LLM consumption. Strips ads, navigation, and boilerplate to extract just the content.

Why It's Useful

AI agents need web content in a format they can understand. MDWB fetches pages and converts them to clean Markdown, perfect for feeding into LLM context windows.

Key Features

  • Website to Markdown conversion
  • Content extraction (reader mode)
  • JavaScript rendering support
  • Clean output formatting

Tech Stack

RustHTML parsingMarkdownHTTP client

Synergies

TRUCompress fetched content for maximum token efficiency
CMStore fetched content as memories

AADC

ASCII Art Diagram Corrector

15

Fixes malformed ASCII art diagrams generated by AI. Corrects alignment, box characters, and connection lines.

Why It's Useful

AI models often generate ASCII diagrams with alignment issues, broken lines, or inconsistent characters. AADC automatically detects and fixes these problems.

Key Features

  • ASCII diagram detection
  • Alignment correction
  • Box-drawing normalization
  • Line connection repair

Tech Stack

RustPattern matchingText processing

Synergies

S2PClean up diagrams in generated prompts
CMStore corrected diagrams as memories

CAUT

Coding Agent Usage Tracker

28

Tracks LLM provider usage across multiple coding agents. Monitors API calls, token consumption, and costs.

Why It's Useful

When running multiple AI agents simultaneously, costs can spiral. CAUT provides visibility into which agents are using how many tokens and at what cost.

Key Features

  • Multi-provider usage tracking
  • Token consumption monitoring
  • Cost estimation
  • Usage alerts and reporting

Tech Stack

RustSQLiteAPI monitoring

Synergies

RANONetwork observations feed usage data
NTMTrack usage per NTM-managed session
MailUsage alerts via Agent Mail

Get Started

The fastest way to set up the entire flywheel ecosystem is with ACFS. One command, 30 minutes, and you're ready to go.

curl -fsSL https://raw.githubusercontent.com/Dicklesworthstone/agentic_coding_flywheel_setup/main/install.sh | bash -s -- --yes --mode vibe

Or use the step-by-step wizard for guided setup.