AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Memory & Context/
okf-agent-memory
okf-agent-memory logo

okf-agent-memory

Active·★ 827·MIT·Updated 2026-10-21
★ Hidden Gem

OKF Agent Memory provides a domain-neutral, Git-native persistent project memory for AI agents, leveraging the Dual-Memory Agent Architecture to prevent context bloat and memory rot. It uses an ultra-compact behavioral codex and a queryable OKF v0.2 knowledge bundle, with blazing-fast, zero-cost local retrieval.

okf-agent-memory sits in the Memory & Context category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Dual-Memory Cognitive Architecture (DMAA) to eliminate prompt bloat.. A representative use case is Software Engineering: Managing architecture decisions, code references, and operational constraints.. The listed license is MIT. GitHub stars are currently 827. Relevant tags include AI Agents, Persistent Memory.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#AI Agents#Persistent Memory#Knowledge Base#Git-Native#RAG#Context Management#Go#LLM
$ Install
$ git clone https://github.com/okf-memory/okf-agent-memory.git && cd okf-agent-memory && make build
↗ Visit site★ GitHub
01

Features

01Dual-Memory Cognitive Architecture (DMAA) to eliminate prompt bloat.
02Blazing fast performance with in-memory BM25 search (<300µs) and graph validation (~4ms).
03100% Git-native, zero vendor lock-in, and zero API costs for memory retrieval.
04Built on Google's Open Knowledge Format (OKF) v0.2 for standardized agent knowledge.
05Solves context bloat and memory rot through progressive disclosure and Search-Before-Write principle.
02

Why choose it

+Dual-Memory Cognitive Architecture (DMAA) to eliminate prompt bloat.
+Blazing fast performance with in-memory BM25 search (<300µs) and graph validation (~4ms).
+Software Engineering: Managing architecture decisions, code references, and operational constraints.
+Supports 4 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Go
Runtime
Verified via docs
Git
Version Control
Verified via docs
MCP
Protocol
Verified via docs
LLM Agents
Integration
Verified via docs
05

Quick start

1
$ git clone https://github.com/okf-memory/okf-agent-memory.git
2
$ cd okf-agent-memory
3
$ make build
06

Use cases

↳Software Engineering: Managing architecture decisions, code references, and operational constraints.
↳Scientific Research & Literature Reviews: Organizing and querying research findings and insights.
↳Coaching & Operations: Storing client session history, ethical guidelines, and runbooks.
↳Multi-Agent Collaboration: Providing a shared, auditable knowledge base for autonomous agents.
07

Alternatives

⚡Top VS:
VSmori★32→VSmnemosyne★151→VSfava-trails★26→VSagents-remember★29→
mori logo
mori★ 32
mori MCP server — A shared memory layer for AI coding agents — one that compounds.
VSCompare→
mnemosyne logo
mnemosyne★ 151
Evidence-backed memory for AI agents: local-first recall, temporal history, tested skills, and gradual migration.
VSCompare→
fava-trails logo
fava-trails★ 26
🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.
VSCompare→
agents-remember logo
agents-remember★ 29
`Agents Remember` is a Drift-aware repository memory for coding agents in complex codebases. Captures what code can't say on its own! Retrieves memory by path, semantic search, and relationship (code-graph).
VSCompare→
memo logo
memo★ 24
Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.
VSCompare→
memorycrystal logo
memorycrystal★ 12
Persistent memory for AI agents — OpenClaw plugin + MCP server
VSCompare→
mex logo
mex★ 1.8k
Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
VSCompare→
cli logo
cli★ 66
Git-native context engineering CLI and MCP server for AI coding agents. Keep specs, ADRs, rules, plans, and project knowledge in Git.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
okf-memory /
okf-agent-memory
↗

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

827MIT
Last commit1d ago
StatusActive
CategoryMemory & Context
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.