Alternatives to Imcodes

A persistent, file-based memory layer for coding agents that lives as a brain/ Markdown folder in your repo.

Local-first memory layer that gives your AI coding agent a SQLite file it can recall from between sessions.

LangSmith is agent and LLM observability: trace, monitor, and evaluate AI agents in cloud, BYOC, or self-hosted.

Arena AI ranks chat models, coding agents and fullstack builds on live head-to-head human votes.

AppWorld is a simulated-world benchmark for evaluating AI coding agents across 9 apps and 457 APIs.

Open-source, self-hosted memory layer that gives AI agents persistent recall via hybrid retrieval.

Self-hosted AI agent with a browser UI, markdown memory on disk, and a cron scheduler that runs while you're offline.

Open-source, self-hosted memory runtime that gives AI agents governed memory with tamper-evident audit receipts

Mem0 is an AI memory layer that gives agents and apps persistent context across sessions

Local, MIT-licensed token and cost observability for AI coding agents — reads the logs your agents already write.

OpenJudge is an Apache 2.0 open-source AI evaluation framework shipping 50+ benchmark-validated graders for agents, LLMs, code, math, and multimodal models.

Open-source orchestration layer from AgentSea for building and launching computer-use agents locally, in Docker, or on cloud VMs.

Three markdown files that give any AI coding agent persistent memory between sessions — no framework, no database, just git.

Local-first memory layer for Claude Code and OpenCode that scores memories by whether they actually worked.

Self-hosted AI agent harness that auto-builds, sandbox-tests, and shares its own tools over MCP

Rover runs multiple AI coding agents in parallel, each in its own isolated sandbox on your local machine.

Local-first coding agent memory that records issues, failed attempts and fixes inside your repo and feeds them back to Claude Code, Cursor or Codex at session

Run AI coding agents in isolated cloud sandboxes — locally on your Mac or delegated from Slack, Linear, and GitHub.

CogniMemo is an API-first persistent memory layer that gives your AI agents structured long-term recall across sessions.

Agent evaluation platform that simulates voice and chat agents, traces production, and scores hallucinations before customers hit them

Mastra is an open-source TypeScript agent framework for durable agents, typed workflows, and built-in evals.

Open-source benchmark that scores AI agents on real, multi-step software-company work tasks.

E2B spins up isolated Linux sandboxes per second so AI agents can run code, process data, and use tools without touching your host.

OMNI is an open-source shell hook that shrinks terminal output before your coding agent reads it, so it stops paying twice for bytes

Vercel deploys web apps and AI agents from Git with preview URLs, a global CDN, sandboxed VMs, and one AI Gateway.

Accordion is a free, MIT-licensed pi extension that shows your coding agent's entire context window as blocks you can fold, unfold, and steer.

Loomal is a payments layer for agentic commerce — paywall an API or MCP tool and get paid per call in USDC on Base.

Free MIT-licensed macOS menu bar app that tracks quota windows, spend, and burn pace for 13 AI coding providers

SWE-ReX is a runtime interface for sandboxed shell execution, letting AI agents run commands on any environment.

Dedalus Labs boots full Linux VMs for AI agents in under 50ms with per-second active-compute billing.