|
x · local coding agent
x — a local coding agent. Wraps Claude through Claude Code's CLI. Strict-write verification on every file action. No API keys.
|
82 % |
|
cot. - Open-source observability for AI agents
cot is the open-source observability layer for AI agents. Trace every session from Claude Code, Cursor, Codex and OpenCode, and improve security, cost and us...
|
82 % |
|
Cori — the execution engine for agent-designed workflows
Describe the work once in chat. Cori saves it as a real program on your machine — typed TypeScript on Temporal, deterministic and testable, with zero LLM cal...
|
81 % |
|
Reasonwork — Get Paid for Your Coding Agent Sessions
Reasonwork turns finished Claude Code, Codex and Cursor CLI sessions into reviewed, priced, rewarded contributions — with the privacy pass running locally, b...
|
81 % |
|
Leo, a research-first writing agent for your terminal
Leo is an open-source terminal agent that reads what ranks, researches with sources, finds what competitors miss, and writes a cited draft. Built on the Clau...
|
81 % |
|
Decision intelligence for AI-assisted engineering | Oka
The institutional knowledge layer for AI-assisted software development. Every session builds on the last.
|
80 % |
|
miii — the open-source alternative to Claude Code. Any model, free forever.
miii is a free, open-source AI coding agent for your terminal and browser. It plans, reads, writes and verifies code. Bring your own keys (Claude, GPT, Gemin...
|
80 % |
|
Cartographer · a map of how you build with coding agents
Cartographer reads the session history your coding agent keeps and tells it back as a story: what you did, what happened, what it meant. Local and private.
|
80 % |
|
Claude Code & Cursor Usage and Cost Tracker — PromptConduit
Open-source CLI that tracks token usage and cost for Claude Code, Cursor, Gemini CLI, and Codex. Local first: every event lands in a file you can read.
|
80 % |
|
SuperClawd | Claude Code, supercharged
Bring your team's coding standards, skills, and guardrails into Claude Code — delivered on demand, every session. Define your rules once; Claude follows them.
|
80 % |
|
Perch — semantic code linting
Perch is an open-source semantic linter powered by SystemOne decision models. Check code for bugs, security issues, and project rules written in plain English.
|
80 % |
|
Kordy: get your product recommended by coding agents
Kordy tracks every recommendation across Claude Code, Codex, Antigravity and Cursor, shows who wins and why, and hands you the fix list to become the default.
|
80 % |
|
Kinjot — notes for AI coding agents
Save the fixes, snippets and explanations your AI coding agent produces. Say “jot that down”, search them later, or let your agents recall them over MCP.
|
80 % |
|
Totus — The command center for coding agents
Self-hosted command center for coding agents. Triage Slack and Linear, plan the work, and ship it with Claude Code or OpenCode — with you in the loop.
|
79 % |
|
stratless · Turn your logs into skills.
Stratless measures how you actually work and installs the skills your history already earned, receipts on every line. Nothing declared, everything counted. R...
|
79 % |
|
Octarin: the AI coding sessions behind every commit
Octarin links every commit and pull request back to the Claude Code, Cursor, Codex, Antigravity, GitHub Copilot, Hermes, and OpenClaw sessions that produced...
|
79 % |
|
Startseite | CodeFathom
AI-assisted product intelligence for teams that ship fast.
|
79 % |
|
Claude Recall: the memory layer for Claude Code and Codex
Local-first searchable memory for Claude Code and Codex. Index every past session from both agents, full-text and semantic search, re-inject context into new...
|
79 % |
|
Linked-Intent Development
Linked-Intent Development — how do you know your agent built what you meant? Write the design in plain English; the agent derives one-line requirements with...
|
79 % |
|
ContextPool - Persistent Memory for AI Agents
Your AI agent forgets everything between sessions. ContextPool fixes that. Extracts engineering insights from past sessions and feeds them back automatically.
|
79 % |
Detected social media networks