|
ml0x, guardrails around your Claude Code agents
ml0x wraps Claude Code with a 5-stage pipeline, budget caps that can't be bypassed, and quality gates that run before you see the output. Free and open source.
|
83 % |
|
SuperLeanAI — Prompt Compression & Token Efficiency Proxy
SuperLeanAI is a prompt compression and context compression proxy for AI coding agents: it debloats verbose tool definitions, MCP server schemas, and Skills...
|
80 % |
|
synapse
Let your best model direct, not type. Send work from Claude Code or any coding tool to a model you bring. Fewer expensive tokens, the same results — up to 68...
|
80 % |
|
BetterC0de — Every coding agent in one desktop workspace
BetterC0de is a free desktop workspace for AI coding agents. Run Claude Code, OpenAI Codex, Cursor Agent and Grok side by side on the same repository with on...
|
80 % |
|
Compaction | Context Optimization for Claude Code and Codex
Reduce token usage in Claude Code and Codex with local context compaction and output shaping. Measured savings, content-free receipts, no prompt or code tele...
|
79 % |
|
Kiwi Code — Built for the final 30%
The first 70% is a demo. The last 30% is the job. Agentic coding for long runs, real systems, and verified work.
|
79 % |
|
env.space
Coding agents should not start from scratch. Keep files, processes, and checkpoints intact between sessions in one persistent Linux sandbox.
|
78 % |
|
Cogni-Code — Persistent memory for AI agents
Give your AI agent a memory that outlasts the session. A persistent, inspectable knowledge graph for Claude Code, Codex CLI, OpenCode, and pi. Plain files on...
|
78 % |
|
postmq — durable messaging and session state for AI agents
Durable messages between AI coding agents and session state that survives restarts — sessions, decisions, rules — one MCP server, a REST API, a dashboard.
|
78 % |
|
Iris — stop shipping agents on vibes
Stop shipping agents on vibes. Score output quality, detect PII and injection attacks, enforce cost thresholds across all your agents. Open-source core, self...
|
78 % |
|
Promptolian: Context Reliability Proxy for AI Agents
|
78 % |
|
Tether — Session Multiplexer for Agentic CLI Tools
One window for every AI coding session. Manage Claude Code, Codex CLI, and more across local, SSH, and Coder workspaces with raw PTY fidelity.
|
78 % |
|
Tokenade — cut your AI coding agent's token bill
Cut the token usage of Claude Code, Cursor, Codex and Copilot. Ranked #1 on the Token-Harness Optimizer Leaderboard. Zero config, one-command install.
|
78 % |
|
1ShotGen — Make your coding agent get it right the first time.
1ShotGen turns a one-sentence idea into a precise, buildable AI prompt for coding agents like Claude Code, Cursor and Codex. One line in. One precise build p...
|
78 % |
|
KlaatAI — AI Coding Assistant, 35 Models, One Plan
One subscription for AI chat, terminal coding, and API. Klaatu-o1 routes 35 frontier models and maps your code with Code Graph — frontier power, lower cost.
|
78 % |
|
Termight — the cockpit for your coding agents
Termight is an agent-native terminal. Run Claude Code, Codex, Gemini, or opencode inside it and supervise the whole fleet: run spines, review and merge gates...
|
78 % |
|
Memlin — SAVE TIME. SAVE TOKENS. KEEP MOVING.
Shared memory for your AI agents. One line in your repo — the real context resolves at call-time, scoped and cited. Not a rules-file dump. Works in Claude Co...
|
78 % |
|
cot. - Agent Observability for Coding Agents
Self-hosted observability for AI coding agents. Trace sessions from Claude Code, Cursor, and Codex: browse timelines, search traces, and review usage metrics...
|
78 % |
|
Relay: self-improving AI agents for coding
The only harness you need for coding. Relay keeps what every run learns, re-tests every task, and runs on your machine with your model.
|
78 % |
|
osnova, a deterministic code map for AI coding agents
Osnova indexes a repository into a symbol and call graph and answers your coding agent with exact file and line. Same commit, same answer. Install it from an...
|
78 % |
Detected social media networks