Generated banner for brainapi2
Generated logo for brainapi2

brainapi2

Memory server

First committed by ChrisCoder9000

Published in Lumen-Labs/brainapi2. Publisher page

551 GitHub stars

What it is

BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications.
— the description by ChrisCoder9000

Summary from the brain’s metadata

BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications.

How it works

Memory model: Hybrid

AutoGineer overview, from the brain’s own files

Memory model: Hybrid. Folders: .github (agent config, 5 files); bin (scripts, 1 file); docs (docs, 36 files); scripts (scripts, 10 files); src (source code, 289 files); tests (tests, 88 files).

Folders
FolderRoleFiles
.githubagent-config5
binscripts1
docsdocs36
scriptsscripts10
srcsource-code289
teststests88
benchmarksfolder125
consolefolder27
deployfolder12
licensesfolder1
mcp-stdio-http-bridgefolder10
pluginsfolder1
tuifolder54

Requirements

Runtimes: Python >=3.11,<4.0.0

Databases: Milvus, MongoDB, Neo4j, PostgreSQL, Redis

API keys (by name): BEARER_TOKEN, BEDROCK_SECRET_ACCESS_KEY, BEDROCK_SESSION_TOKEN, BRAINPAT_TOKEN, DEEPSEEK_API_KEY, DOCPARSER_TOKEN, OPENAI_API_KEY, PLUGIN_PUBLISHER_API_KEY

Works with: Claude Code, OpenAI Codex, GitHub Copilot, Cursor, Kiro, OpenCode, Amp, Cline, JetBrains Junie, Devin (ex-Windsurf)

Set it up

  1. Not scanned by AutoGineerThe author’s README also describes installing it from a clone of its repository. Read its install section: AutoGineer did not scan that path. https://github.com/Lumen-Labs/brainapi2/blob/4493e08ef690d46bd0abb43d63e86493137195c2/README.md#%EF%B8%8F-run-it-locally-dev-mode
  2. First committed by ChrisCoder9000. Published in Lumen-Labs/brainapi2. Licence: Business Source License 1.1.

Usage

AutoGineer’s guidance for this type of brain

Add the server to your AI tool’s MCP configuration (see Set it up); your agent then stores and recalls memories through its tools.

Documentation by ChrisCoder9000

The licence does not allow AutoGineer to copy these files. Read the documentation at the source

512 files · 512 not served here

Advantages

  • Local-first: the memory stays in files or a database on your own machine (a rule-derived fact from the brain’s files, evidence: README.md)
  • Works with 10 MCP clients (a rule-derived fact from the brain’s files, evidence: README.md)

Limitations

  • Needs an API key (BEARER_TOKEN, BEDROCK_SECRET_ACCESS_KEY, BEDROCK_SESSION_TOKEN) (a rule-derived fact from the brain’s files, evidence: README.md)
  • Needs a database (Milvus, MongoDB, Neo4j) (a rule-derived fact from the brain’s files, evidence: README.md)
  • Link-only: AutoGineer links to the files instead of serving them (a rule-derived fact from the brain’s files)

Security

Risk level: Low risk

This brain runs

Agent instructions that run or fetch something (7)

  • benchmarks/AGENTS.md: ./search.sh evaluate --dataset data/search_esci.jsonl --brain searchbenchesci --run search-esci
  • benchmarks/AGENTS.md: ./search.sh --brain searchbenchwands evaluate --dataset data/search_wands.jsonl --run search-wands-passages-k50 --channels passages --k 50 --ks 5,10,20,50
  • benchmarks/AGENTS.md: ./search.sh --brain searchbenchwands evaluate --dataset data/search_wands.jsonl --run search-wands-passages-k50 --channels passages --k 50 --ks 5,10,20,50 --skip-ingest
  • benchmarks/AGENTS.md: ./search.sh --brain searchbenchwandsgraph evaluate --dataset data/search_wands.jsonl --run search-wandsgraph-communities-k50 --channels communities --k 50 --ks 5,10,20,50 --ingest-graph
  • benchmarks/AGENTS.md: ./search.sh report --run <run_id>
  • benchmarks/AGENTS.md: After any completed evaluate/report that produces a successful scored run, ensure the suite entry in `REPORTS.json` reflects it.
  • benchmarks/AGENTS.md: TUI / `brainapi start` may run from `~/.brainapi/source`, not this workspace.
  • Low risk: scripts-present (scripts/install_extras.py)

Attribution and licence

First committed by
GitHub avatar of ChrisCoder9000ChrisCoder9000
Declared authors
  • Christian (declared in pyproject.toml)
Publisher
Lumen Labs (Community)
Source
Lumen-Labs/brainapi2 · commit 4493e08
Licence
Business Source License 1.1 (The licence does not allow AutoGineer to copy these files.)
Synced
Contributors
ChrisCoder9000, shreytiwari09

AutoGineer is not affiliated with or endorsed by ChrisCoder9000 or Lumen Labs.

Install from source

The licence does not allow AutoGineer to copy these files. Lumen-Labs/brainapi2 at 4493e08