Back to Topics Directory
Topic Hub

#ai-agents (30 Repositories)

Ranked open-source repositories tagged with #ai-agents, scored by pull request acceptance likelihood and maintainer engagement velocity.

Topic Avg Merge Rate

93.9%

Avg Review Latency

16.5h

Filter by language

30 repositories tagged #ai-agents

B TierPython 142

bjgreenberg/senior-engineering-partner

A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS). Security-first, phase-aware engineering discipline with a spec→plan→TDD→verify workflow.

99.1%
Merge Rate
<1h
First Review
100%
1st-Timers
1
Maintainers
S TierRust 354

fajarhide/omni

Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.

95.1%
Merge Rate
1h
First Review
88%
1st-Timers
2
Maintainers
S TierRust 232 11 GFIs

DecapodLabs/decapod

Repo-native governance kernel for bounded, convergent, proof-backed agent work.

95.4%
Merge Rate
12h
First Review
100%
1st-Timers
2
Maintainers
B TierTypeScript 90

olo-dot-io/Uni-CLI

Operation-first Agent-Computer Interface for real software—discover one executable path across APIs, browsers, desktops, local tools, and MCP.

100.0%
Merge Rate
1h
First Review
100%
1st-Timers
1
Maintainers
S TierTypeScript 587

Pasta-Devs/Marinara-Engine

AI frontend

92.6%
Merge Rate
13h
First Review
83%
1st-Timers
18
Maintainers
S TierRust 385 5 GFIs

multikernel/sandlock

The lightest AI sandbox. A process-based sandbox for Linux, no container, no VM, no privilege, no prompt injection

90.1%
Merge Rate
2h
First Review
80%
1st-Timers
12
Maintainers
S TierPython 104 41 GFIs

Metabuilder-Labs/tokenjam

Token Efficiency For AI Agents

90.7%
Merge Rate
21h
First Review
85%
1st-Timers
6
Maintainers
S TierTypeScript 246

h0x91b/dev-3.0

Mission control for the One Person Studio — run a fleet of AI coding agents in parallel without losing your mind. Kanban + git worktrees + tmux for Claude Code, Codex, Gemini CLI, OpenCode and any shell agent. Not an IDE.

95.8%
Merge Rate
1d
First Review
64%
1st-Timers
11
Maintainers
S TierGo 23.0k

micro/go-micro

A Go agent harness and service framework

98.6%
Merge Rate
8h
First Review
100%
1st-Timers
2
Maintainers
S TierSwift 483

umputun/agterm

A genuinely good terminal

92.8%
Merge Rate
2h
First Review
80%
1st-Timers
24
Maintainers
S TierGo 77

avivsinai/agent-message-queue

File-based message queue for local agent-to-agent communication (Maildir-style)

90.5%
Merge Rate
14h
First Review
75%
1st-Timers
3
Maintainers
S TierPython 5.2k

huangruiteng/loopx

Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.

95.4%
Merge Rate
18h
First Review
63%
1st-Timers
22
Maintainers
B TierJavaScript 171

echopath-labs/openDomain

Git-native, evidence-backed domain semantic layer for AI agents and human maintainers.

100.0%
Merge Rate
<1h
First Review
100%
1st-Timers
1
Maintainers
B TierJavaScript 173 4 GFIs

coco-research/coco

Meet Coco. A superintelligent agent framework powered by an advisory board of 389 world-class minds. Scale your AI assistant into a complete engineering department with 142 skills, 277 commands, and persistent state. Universal compatibility. Local privacy. Free and open source.

93.1%
Merge Rate
2h
First Review
50%
1st-Timers
0
Maintainers
S TierJavaScript 931 2 GFIs

webbrain-one/webbrain

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

92.3%
Merge Rate
2d
First Review
100%
1st-Timers
9
Maintainers
S TierTypeScript 83 1 GFIs

Bike4Mind/bike4mind

The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.

90.7%
Merge Rate
5h
First Review
85%
1st-Timers
27
Maintainers
B TierTypeScript 226 6 GFIs

Get-Concord-AI/concord-mcp

"Google Workspace" for your AI Agents

97.1%
Merge Rate
2d
First Review
100%
1st-Timers
0
Maintainers
B TierPython 206

aivrar/portable-hermes-agent

Hermes Agent made portable desktop for Windows — 100 tools, GUI, local models via LM Studio, TTS, Music, ComfyUI, workflows, tool maker. No install. No Docker. No admin rights.

97.0%
Merge Rate
1h
First Review
100%
1st-Timers
0
Maintainers
S TierTypeScript 332 1 GFIs

vuejs-ai/vue-tui

The Vue framework for terminal UIs. SFC & JSX, Yoga flexbox, HMR, and testing out of the box.

91.4%
Merge Rate
5h
First Review
100%
1st-Timers
5
Maintainers
B TierJavaScript 117

RapierCraftStudios/ForgeDock

ForgeDock — autonomous AI dev pipeline for Claude Code. GitHub as agent memory: issue in, PR out.

97.5%
Merge Rate
1h
First Review
100%
1st-Timers
1
Maintainers
S TierGo 275

FootprintAI/Containarium

Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrough, MCP-native CLI

95.8%
Merge Rate
2d
First Review
100%
1st-Timers
3
Maintainers
S TierTypeScript 879

MemTensor/memmy-agent

🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.

86.7%
Merge Rate
13h
First Review
87%
1st-Timers
10
Maintainers
S TierGo 353 2 GFIs

YoanWai/agent-manager

The fastest workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.

91.9%
Merge Rate
22h
First Review
80%
1st-Timers
7
Maintainers
S TierTypeScript 495 4 GFIs

liliu-z/stashbase

Turn local files into searchable context for AI agents.

87.4%
Merge Rate
5h
First Review
67%
1st-Timers
13
Maintainers
S TierPython 495

avibe-bot/avibe

The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex & OpenCode from your browser or any chat app.

92.5%
Merge Rate
20h
First Review
88%
1st-Timers
5
Maintainers
S TierPython 207

fu351/Doberman-Core

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.

93.8%
Merge Rate
1d
First Review
83%
1st-Timers
11
Maintainers
S TierTypeScript 143

epilande/ccmux

🔮 Run all your AI coding agents (Claude Code, Codex, Cursor, ...) in tmux: jump to the one that needs you, spawn them into worktrees, and hand work between them

94.2%
Merge Rate
5h
First Review
100%
1st-Timers
2
Maintainers
S TierTypeScript 278 13 GFIs

SirAllap/agentglass

🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dangerous until you say go. From your desk or your phone.

96.5%
Merge Rate
2d
First Review
100%
1st-Timers
3
Maintainers
S TierTypeScript 352

openwong2kim/wmux

Run Claude Code, Codex & Gemini in parallel on Windows & macOS — git worktree fan-out with atomic hunk adoption, approval gates, reboot-surviving sessions

90.6%
Merge Rate
2d
First Review
93%
1st-Timers
7
Maintainers
S TierGo 679

kdlbs/kandev

AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.

91.3%
Merge Rate
12h
First Review
61%
1st-Timers
17
Maintainers