agentkeeper

About agentkeeper

AgentKeeper Cognitive continuity infrastructure for long-lived AI agents. Your agent survives model switches, crashes, context-window limits, and restarts — with the same identity, memory, and priorities it had before. Why this exists Agents don't fail because they forget facts. They fail because they lose cognitive continuity — their state, priorities, and identity drift the moment the model changes, the context window fills, or the process restarts. AgentKeeper treats this as a systems problem, not a memory problem. Install Zero required dependencies. No external infrastructure.

agent-memory agentic-ai agents ai-agents ai-memory anthropic claude cognitive-continuity cross-model embeddings

Quick Facts

Stars	117
Forks	17
Language	Python
Category	MCP Server
License	MIT
Quality Score	55.304/100
Last Updated	2026-05-20
Created	2026-02-24
Platforms	claude-code, gemini, mcp, python
Est. Tokens	~27k

Compatible Skills

These tools work well together with agentkeeper for enhanced workflows:

vektori — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (57%)
throughline — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (55%)
honcho — semantic(0.43)+complementary+same_lang+shared_platform (55%)
powermem — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (55%)

More MCP Server Tools

Explore other popular mcp server tools:

n8n ⭐ 189.3k
ECC ⭐ 187.4k
everything-claude-code ⭐ 186.6k
dify ⭐ 142.3k
open-webui ⭐ 138.2k
gemini-cli ⭐ 104.5k
awesome-mcp-servers ⭐ 86.1k
servers ⭐ 86.1k
ragflow ⭐ 79.0k
lobehub ⭐ 77.5k

View all MCP Server tools →

Popular Python Agent Tools

AutoGPT ⭐ 184.5k · Agent Tool
hermes-agent ⭐ 162.8k · Codex Skill
langflow ⭐ 148.7k · Agent Tool
open-webui ⭐ 138.2k · MCP Server
skills ⭐ 137.5k · Claude Skill

Frequently Asked Questions

What is agentkeeper?

agentkeeper is Cognitive continuity infrastructure for long-lived AI agents — cross-model state reconstruction, semantic recall, cognitive compression.. It is categorized as a MCP Server with 117 GitHub stars.

What programming language is agentkeeper written in?

agentkeeper is primarily written in Python. It covers topics such as agent-memory, agentic-ai, agents.

How do I install or use agentkeeper?

You can find installation instructions and usage details in the agentkeeper GitHub repository at github.com/Thinklanceai/agentkeeper. The project has 117 stars and 17 forks, indicating an active community.

What license does agentkeeper use?

agentkeeper is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse MCP Server tools