林森

Corpus Hub contributor since 2026-10-22

林森's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.

1corpus

1selected commit

14files

1,550lines

★ 1GitHub stars on repo

Totals across every corpus @l1871276598-dotcom appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.

What an agent can do with the research-agent-memory corpus

l1871276598-dotcom/research-agent-memory: Local-first, auditable, human-governed memory and learning layer for AI agents

Look up how research-agent-memory implements agent-memory, ai-agents, codex, with answers cited to file and line.
Reuse a worked example: the commit “implement ADR-007 Heuristic Pattern Engine, Mode…” (14 files · Python).
Answer from research-agent-memory's real Python source instead of memory (AI, prompts and agents).

Example questions

How does research-agent-memory implement agent-memory?
What does tests do in research-agent-memory?

Paste it into your AI agent. It clones the repo at the pinned commit and indexes it on your machine.

Search the GitHub repository l1871276598-dotcom/research-agent-memory with XERJ (https://hub.xerj.org/corpus/l1871276598-dotcom--research-agent-memory).
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/l1871276598-dotcom/research-agent-memory research-agent-memory && git -C research-agent-memory checkout b7cf5cfdd80f8ff7f57feab3fba8c4ef9f0e8f46
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./research-agent-memory --url http://127.0.0.1:9200 --prefix research-agent-memory --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: MIT. Keep the copyright notice and credit the authors.

corpus l1871276598-dotcom--research-agent-memory · AI, prompts and agents
Related corpora: fastmcp, agno, Buzburg/Swarmojo, sickn33/tidal-mcp
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 1

l1871276598-dotcom/research-agent-memory

b7cf5cfdd8 feat(learning_loop): implement ADR-007 Heuristic Pattern Engine, Mode…

selected commit: 14 files · 1,550 lines · Python · tests, src/models, src/learning_loop

The corpus is the whole repository at the pinned commit, not only the files of the selected commit.

selected · in licence reviewcorpus l1871276598-dotcom--research-agent-memoryAIMITagent-memoryai-agentscodexhuman-in-the-looplocal-firstmcp agreed 2026-10-22

Not installable yet: this corpus is not in the hub registry until its licence review passes, so xerj corpus add and xerj ask cannot fetch it. It becomes installable when this card says live in the hub.

[![XERJ Corpus Hub contributor](https://hub.xerj.org/contributors/l1871276598-dotcom/badge.svg)](https://hub.xerj.org/contributors/l1871276598-dotcom)

Included with the author's permission (email, 2026-10-22), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.