SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 ai-coding Open-Source Projects
-
ruflo
🌊 The leading agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
Project mention: How I tracked down a 36GB memory leak in a Claude Code memory server | dev.to | 2026-06-21Upstream writeup with the full retainer trace: ruvnet/ruflo#2432. The wrapper itself, if you're curious: jazz-max/ruflo-hub.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
DeepSeek-Reasonix
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
Project mention: DeepSeek open-sources inference optimizations with 60–85% faster generation [pdf] | news.ycombinator.com | 2026-06-27Have you tried reasonix?
https://github.com/esengine/deepseek-reasonix
-
serena
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
You should add Serena https://github.com/oraios/serena to your list.
Serena gives you symbol-level navigation, reading, and editing via tree-sitter. So you're already getting much of what CoderLM offers — plus Serena has editing capabilities(replace symbol body, insert before/after symbol, rename). GitNexus goes further with the graph/impact analysis layer on top.
I personally use Serena and GitNexus.
The case for using both
- GitNexus tells you what to change (impact analysis, dependency maps, blast radius) -
kilocode
Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.
The coding space is especially crowded: OpenCode, Droid, OpenHands, KiloCode, Crush, Aider, and Pi, to name a few. Autonomous agents like OpenClaw and Hermes are hugely popular and burn through tokens. Agent orchestrators like Paperclip and Conductor are a legitimate category now too, and we’ll likely see more vertical harnesses soon.
-
code-review-graph
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Project mention: Code-review-graphv 2.1.0, 8× fewer tokens for code reviews via structural graph | news.ycombinator.com | 2026-04-03• True zero-config install — one command across 7 platforms
Tech: Python + Tree-sitter + SQLite (WAL) + FastMCP. 572 tests.
https://code-review-graph.com
GitHub: https://github.com/tirth8205/code-review-graph
pip install code-review-graph && code-review-graph install
-
claude-context
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Claude Code doesn't do anything with semantic search or embeddings out of the box. They use a simple grep tool instead.
Neither does OpenAI's Codex CLI - you can confirm that by looking at the source code https://github.com/openai/codex
Cursor and Windsurf both use semantic search via embeddings.
You can get semantic search in Claude Code using this unofficial plugin: https://github.com/zilliztech/claude-context
-
loop-engineering
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
Meanwhile, the ecosystem materialized. obra/superpowers shipped a complete software development methodology built on composable skills — 1,276+ stars and growing. The cobusgreyling/loop-engineering repo cataloged patterns from Osmani and Cherny into a practical reference.
-
codeburn
See where your AI coding tokens go. Interactive TUI dashboard for Claude Code, Codex, and Cursor cost observability.
Project mention: Show HN: macOS menu bar gauges for your Claude Code quota | news.ycombinator.com | 2026-06-10I use codeburn, has both terminal and menu bar versions. Works quite well - https://github.com/getagentseal/codeburn
-
MonkeyCode documents managed development environments and AI task management for teams, including a self-hosted option. That makes it relevant when the requirement moves from “wrap my local command” to “coordinate development tasks across people and controlled environments.” The little runner above is not a MonkeyCode integration or benchmark; it is a way to make the operational questions visible before evaluating a larger system.
-
crystal
(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, compare approaches & manage AI-assisted development workflows in one desktop app. (by stravu)
Option 4: Integrated environment. Tools like Nimbalyst that treat markdown as a first-class concern alongside code. Newer approach, fewer options, but addresses the fundamental problem of fragmented context.
-
Project mention: How I Run Claude Code in Docker with a Web UI and Headless Browser | dev.to | 2026-03-21
GitHub: https://github.com/CoderLuii/HolyClaude Docker Hub: https://hub.docker.com/r/coderluii/holyclaude Website: https://holyclaude.coderluii.dev
-
codeburn
See where your AI coding tokens go. Interactive TUI dashboard for Claude Code, Codex, and Cursor cost observability. (by AgentSeal)
Repo: https://github.com/AgentSeal/codeburn Open source, MIT.
-
pro-workflow
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.
Project mention: Stop Rebuilding Your Claude Code Setup - Scaffold It Once with Worclaude | dev.to | 2026-04-16The workflow draws from Boris Cherny's tips (creator of Claude Code at Anthropic), patterns from Affaan Mir's everything-claude-code (Anthropic hackathon winner), Karpathy's coding principles, and community repos like pro-workflow.
-
-
pilot-shell
How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quality enforcement on all levels. Make your agents production-ready.
Project mention: Pilot Shell: Spec-driven plans; enforced quality gates; persistent knowledge | news.ycombinator.com | 2026-07-03 -
open-cowork
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.
-
haft
Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more.
Project mention: Structured reasoning for AI coding tools – Quint Code | news.ycombinator.com | 2025-12-18 -
BitFun
BitFun is a desktop-grade Agent runtimeand a ready-to-use suite of desktop Agent applications.with built-in Code Agent 、 Cowork Agent、Computer Use. It has memory, personality, and the ability to evolve over time
Project mention: Show HN: BitFun – An Agentic Development Environment (Rust and TypeScript) | news.ycombinator.com | 2026-03-04 -
-
Project mention: Rulesync – a single source of truth for your coding agent configs | news.ycombinator.com | 2026-05-07
-
Project mention: This Month in Solid: The Road to 2.0 is here, SolidStart 1.3.0 release 😎 | dev.to | 2026-03-05
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree
-
maggy
What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center
Project mention: Maggy – Self-improving AI engineering platform with cross-session memory | news.ycombinator.com | 2026-05-11 -
NOTE:
The open source projects on this list are ordered by number of github stars.
The number of mentions indicates repo mentiontions in the last 12 Months or
since we started tracking (Dec 2020).
ai-coding discussion
ai-coding related posts
-
Build the Failure Path Before You Trust an AI Task CLI
-
Build an Agent Task State Machine Before You Build an Agent
-
Should Your Team Self-Host AI Coding? A MonkeyCode Scorecard
-
Put a Deterministic Gate Between Generated Code and Main
-
Design the Moment an AI Agent Needs Human Input
-
How to Black-Box Test MonkeyCode Task Reliability
-
Threat-Modeling MonkeyCode as a Self-Hosted AI Coding Platform
-
A note from our sponsor - SaaSHub
www.saashub.com | 11 Jul 2026
Index
What are some of the best open-source ai-coding projects? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | ruflo | 63,860 |
| 2 | DeepSeek-Reasonix | 26,538 |
| 3 | serena | 26,076 |
| 4 | kilocode | 25,841 |
| 5 | code-review-graph | 19,357 |
| 6 | claude-context | 12,112 |
| 7 | loop-engineering | 5,499 |
| 8 | codeburn | 4,193 |
| 9 | MonkeyCode | 3,575 |
| 10 | crystal | 3,094 |
| 11 | HolyClaude | 2,415 |
| 12 | codeburn | 1,934 |
| 13 | pro-workflow | 1,907 |
| 14 | Awesome AI Coding Tools | 1,894 |
| 15 | pilot-shell | 1,782 |
| 16 | open-cowork | 1,449 |
| 17 | haft | 1,363 |
| 18 | BitFun | 1,319 |
| 19 | aider-desk | 1,299 |
| 20 | rulesync | 1,208 |
| 21 | parallel-code | 828 |
| 22 | maggy | 699 |
| 23 | wcgw | 666 |
Sponsored
SaaSHub - Software Alternatives and Reviews
SaaSHub helps you find the best software and product alternatives
www.saashub.com