AgentMemory
Self-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + vector recall, and department/team/member isolation. SQLite or Postgres, any OpenAI-compatible LLM
What XERJ indexed
Snapshot
The whole repository at commit 9fc15364c4 (2026-10-19). main is 64 commits ahead.
Selected work
“migrate an install from SQLite to PostgreSQL”. 9 files, 1,482 lines in crates/memory-infrastructure, the project root, crates/memory-server.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-21. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
aiai-agent-memorydockerpostgresqlrustsqliteclaude-codeclaude-code-plugin
Example questions
- How does AgentMemory implement ai?
- Where does AgentMemory handle “migrate an install from SQLite to PostgreSQL”?
- What does crates/memory-infrastructure do in AgentMemory?
Inside the indexed corpus
- Languages by size: Rust 80.4%, TypeScript 16.4%, Shell 2.4%, Python 0.3%, Dockerfile 0.3%.
- On GitHub since 2026-10-18, last push 2026-10-28, 74 commits on main.
- The pin is 64 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub did not match the LICENSE file of hsuanshao/AgentMemory to a standard licence on 2026-10-29 (NOASSERTION). At commit 9fc15364c4 it was reviewed as NONE, and that is the licence the corpus uses.
Contributors
William Chang (@hsuanshao) has 4 selected repositories on the hub.
Their other repository pages: hsuanshao/protoc-gen-gofilter, hsuanshao/golibs, hsuanshao/ctx.
Using XERJ with AgentMemory
- A local search tool for Codex and Cursor AgentMemory is tagged claude-code on GitHub.
- Local code search MCP that uses fewer tokens than grep
- What is agentic memory? A plain answer AgentMemory is tagged agent-memory on GitHub.
- XERJ vs Mem0, Zep, Letta and Cognee for agent memory
The prompt
Paste it into your AI agent. It clones hsuanshao/AgentMemory at the pinned commit and indexes it on your machine.
Search the GitHub repository hsuanshao/AgentMemory with XERJ (https://hub.xerj.org/corpus/hsuanshao--agentmemory). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/hsuanshao/AgentMemory AgentMemory && git -C AgentMemory checkout 9fc15364c461b3856738e05ba8a171f3b720ad1e 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./AgentMemory --url http://127.0.0.1:9200 --prefix agentmemory --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: check the LICENSE file. Keep the copyright notice and credit the authors.
Related
William ChangAI, prompts and agents corporachromaxerj-blogpostsxerj-columnarandreimerlescu/rocliliang-cn/cortexdbaistastudio/myc
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.