AgentScout / Tasks / Memory for agents / Codebase context and code search

Codebase context and code search tools for agent memory

Context layers and code search that help agents understand large codebases with fewer tokens. Of the 114 tools on our memory for agents page, 8 fit this narrower job. By pricing: 5 open source, 1 source-available, 1 free or freemium, 1 paid, usage-based or enterprise. The most-starred open repos here are Codebase Memory MCP (46,717 stars), Cognee (32,405 stars), Graphiti (31,819 stars). Most come from the memory & RAG (5), coding (2), MCP servers (1) categories.

Updated

Codebase Memory MCP logo

Codebase Memory MCP

MCP serversOpen source

MCP server that indexes codebases into a persistent knowledge graph so coding agents can look up structure quickly.

Added

Cognee logo

Cognee

memory & RAGOpen source + cloud

Open-source memory platform that builds knowledge graphs so agents keep long-term memory.

Added

Graphiti logo

Graphiti

memory & RAGOpen source

Builds real-time, temporal knowledge graphs that serve as memory for AI agents.

Added

Context Mode logo

Context Mode

codingSource-available + cloud

Context window optimizer for coding agents that sandboxes tool output and persists session memory.

Added

Zep logo

Zep

Newmemory & RAGFreemium

Context layer that unifies business data, documents and conversations into memory so agents complete tasks correctly.

Added

LazyCodex logo

LazyCodex

NewcodingOpen source

Agent harness for Codex that adds project memory, planning, execution and verified completion for complex codebases.

Added

ktx logo

ktx

Newmemory & RAGOpen source

An open-source context layer for data and analytics agents that gives Claude Code, Codex and other agents a self-improving map of your warehouse, metrics and business definitions.

Added

Tulimoa Memory logo

Tulimoa Memory

Newmemory & RAGUsage-based

Tulimoa Memory is a hosted, shared memory store for AI agents and agent swarms. Agents write what they learn into it during the day; overnight a separate model sorts those notes into a knowledge graph with associative recall, and each agent starts the morning with a short briefing so it reads less and knows more. It is billed per call, with starting credit to try it.

Added

GitHub repos (7)

RepoGitHub starsLicenceLast push
Codebase Memory MCP ↗46,717MIT2026-10-22
Cognee ↗32,405Apache License 2.02026-10-16
Graphiti ↗31,819Apache License 2.02026-10-23
Context Mode ↗30,192Elastic License 2.0 (source-available)2026-10-23
Zep ↗4,969Apache 2.0 for the examples and integrations repo; Zep Cloud itself is a managed service2026-10-20
LazyCodex ↗3,792—2026-10-23
ktx ↗1,620—2026-07-07

7 repos. Stars and licence come from each repo, checked when the listing was last verified.

FAQ

What are the best AI tools for memory for agents focused on codebase context and code search?

We list 8. The first three by GitHub stars and featured status are Codebase Memory MCP: MCP server that indexes codebases into a persistent knowledge graph so coding agents can look up structure quickly.; Cognee: Open-source memory platform that builds knowledge graphs so agents keep long-term memory.; Graphiti: Builds real-time, temporal knowledge graphs that serve as memory for AI agents.

Are there free or open-source options?

Yes: 5 open source, 1 source-available, 1 free or freemium, 1 paid, usage-based or enterprise. Pricing is as each maker states it.

More from memory for agents

Tools are grouped by what each says it does. Missing one? Submit it free.

Get the best new AI agents, weekly

One short email with new tools, launches and what's worth trying. Free, unsubscribe anytime.