echo-agent
A self-hosted, long-running AI agent runtime with memory, skills, plugins, and multi-channel integrations
Decision gist · record as of 2026-08-14
Yes, if you need a self-hosted agent that retains memory and improves over time. The framework is actively maintained, has low install friction, and covers real gaps in stateless agent systems. Start with `echo-agent setup` to configure your model API keys. Not suitable if you need a simple one-shot chatbot or prefer fully managed cloud hosting.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11+.
- Setup requires at least one model API key (OpenAI, Claude, or other supported provider).
- Low friction: pure Python wheel with 11 runtime dependencies including aiohttp, pydantic, and loguru.
License · maintenance · safety
MIT (permissive) — MIT license (permissive) allows commercial and private use with minimal restrictions—include a copy of the license and copyright notice.
last release 2026-07-20 (25 days) · last repo commit 2026-08-14 · 928 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 291,031 downloads/mo, #7,976 on PyPI
Alternatives
Verify before relying
pip install "echo-agent[all]"
echo-agent setup
echo-agent run- Whether the four-layer memory system (Working/Episodic/Semantic/Archival) scales efficiently for months or years of continuous operation.
- Performance characteristics of BM25 + FAISS hybrid retrieval under high-volume memory scenarios.
- Actual overhead and latency of the self-evolution engine (trajectory recording, candidate generation, evaluation).
- Whether the tool approval system's three policies (manual/smart/off) cover all real-world risk profiles.
What it is and what it does
Echo Agent is a framework for deploying AI agents that retain memory across conversations and continuously improve their skills from real execution traces. Unlike stateless chatbots, it maintains four layers of cognitive memory (working, episodic, semantic, archival) with automatic decay and contradiction detection to prevent memory bloat over long-term operation. Skills are generated as candidates from execution logs, validated against test cases, and promoted or rolled back—allowing the agent to improve without manual retraining.
The runtime unifies multiple entry points (CLI, HTTP gateway, webhooks, cron jobs, and 12 messaging platforms including Telegram, Discord, Slack, WeChat, Feishu, and DingTalk) into a single shared state and execution context. It enforces safety through tiered tool approval (manual, smart, or off), encrypts credentials at rest, and logs all actions for audit. Designed for self-hosted deployment on your own infrastructure, it supports local-first storage of sessions, memory, execution traces, and secrets.
Use it for
- Run a persistent AI assistant on your server that remembers conversation history and user preferences across weeks or months, improving responses over time.
- Integrate the same agent across multiple communication channels (CLI, Slack, Discord, webhooks) while maintaining unified memory and permissions.
- Deploy an agent that automatically refines its tool-use strategies by analyzing real execution outcomes, with human approval gates for risky operations.
- Build audit-compliant AI workflows where every tool call, decision, and memory update is logged and traceable for compliance or debugging.
- Automate recurring tasks (via cron) while the agent learns from past executions and adapts its approach without code changes.
- Operate a multi-model agent that routes different tasks (reasoning, embedding, approval) to different LLM providers based on cost or capability.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need a self-hosted agent that retains memory and improves over time.
The framework is actively maintained, has low install friction, and covers real gaps in stateless agent systems. Start with `echo-agent setup` to configure your model API keys. Not suitable if you need a simple one-shot chatbot or prefer fully managed cloud hosting.
Install
echo-agent on PyPI
Before you install
Low friction: pure Python wheel with 11 runtime dependencies including aiohttp, pydantic, and loguru. Active maintenance (last commit 2026-08-14, 928 GitHub stars). Requires Python 3.11+. No compiled dependencies reported.
Requires Python 3.11+. Setup requires at least one model API key (OpenAI, Claude, or other supported provider).
License in practice
MIT license (permissive) allows commercial and private use with minimal restrictions—include a copy of the license and copyright notice.
Quickstart
pip install "echo-agent[all]"
echo-agent setup
echo-agent runVerify before relying
- Whether the four-layer memory system (Working/Episodic/Semantic/Archival) scales efficiently for months or years of continuous operation.
- Performance characteristics of BM25 + FAISS hybrid retrieval under high-volume memory scenarios.
- Actual overhead and latency of the self-evolution engine (trajectory recording, candidate generation, evaluation).
- Whether the tool approval system's three policies (manual/smart/off) cover all real-world risk profiles.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 11 packagesaiohttpaiosqlitecroniterfastembedhttpxlogurunumpypydantic-settingspydanticpyyamlquestionary |
| Maintenance | Actively maintained 25 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 291,031 / month, #7,976 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaEnvironment :: ConsoleEnvironment :: Web EnvironmentFramework :: AsyncIOIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseNatural Language :: EnglishOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.11Programming Language :: Python :: 3.12Topic :: Communications :: ChatTopic :: Internet :: WWW/HTTP :: HTTP ServersTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Software Development :: Libraries :: Application Frameworks |
Evidence: echo_agent-0.3.5-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “self-hosted ai agent memory”
- echo-agentEcho Agent is a self-hosted, long-running AI agent runtime that…
- mindroomMindRoom is a multi-agent runtime that deploys AI agents as…
- cogneeCognee builds a self-hosted knowledge graph from ingested data,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also mindroom · pairmux · mem0ai · cognee · hol-guard · openhands · omnigent · stashai · cuga