Reported issues for locus
Pod holds 10 of 10 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.
Back to locus.
Most discussed
MCP server documentation and integration guide
Document how to run the MCP server, configure it in Claude/Cursor/Zed, and how it relates to the v1 skill-based interface. Include a migration path from skill-only to MCP-enhanced.
Read the thread · 2026-03-02 · closed · 1 comment
Implement memory_search tool (FTS)
Full-text search across the palace using grep/ripgrep or SQLite FTS5. Returns ranked results with room path and matched context. This is the primary v2 capability that justifies the MCP layer.
Read the thread · 2026-03-02 · closed · 1 comment
Implement memory_read, memory_write, memory_list tools
Core MCP tools: memory_read(path) fetches a room file, memory_write(path, content) writes atomically with git audit, memory_list(path?) returns the palace index or a room's file list.
Read the thread · 2026-03-02 · closed · 1 comment
Design MCP server architecture
Define the MCP server structure: transport (stdio vs HTTP), tool surface area (memory_read, memory_write, memory_list, memory_search), and how it maps to the underlying palace file structure.
Read the thread · 2026-03-02 · closed · 1 comment
Implement agent suggestion logic
When metrics show oversized context or high retrieval depth, the agent should surface two options: (1) raise the context size limit, or (2) split the room into smaller files. Define the threshold triggers and suggestion message format.
Read the thread · 2026-03-02 · closed · 1 comment
Implement /locus feedback command
Create a /locus-feedback command that captures an explicit user disagreement signal. Records: timestamp, room accessed, query context, user verdict. Stored as an append-only log for later analysis.
Read the thread · 2026-03-02 · closed · 1 comment
feat: post-release document verification skill
Overview
After each version release, several documents need to be verified and updated:
- README roadmap table (add new milestone)
- CHANGELOG.md (add entry)
- spec/mcp-server.md (version-referenced sections)
- PyPI badge / install examples (auto-updated via badge, but verify)
- docs/img/ SVG charts (regenerate from benchmark data)
Proposed Solution
Create a `post-release-verify` skill (or `locus-release` Claude Code skill) that:
- Runs `uv run pytest tests/unit/` — tests MUST
Read the thread · 2026-03-03 · closed · 0 comments
Build Agent SDK entrypoint
Add a Python Agent SDK application that makes Locus runnable as a standalone autonomous agent — not just a skill loaded by Claude Code.
Purpose
- Drives Locus behavior programmatically (navigate palace, read/write rooms, run consolidation)
- Serves as the test harness for benchmark fixtures (#24, #25)
- Foundation for the v0.5 MCP server backend
Design
locus/
agent/
__init__.py
main.py ← entrypoint: accepts palace path + task prompt
config.py ← allowedTool
[Read the thread](https://github.com/Nano-Nimbus/locus/issues/26) · 2026-03-02 · closed · 0 comments
## Most recent
### Write Locus skill for Codex
Port the Claude SKILL.md to a Codex-compatible skill under `.codex/skills/locus/`. Must be expressed in plain markdown with no Claude-specific tooling assumptions.
[Read the thread](https://github.com/Nano-Nimbus/locus/issues/9) · 2026-03-02 · closed · 0 comments
### Define INDEX.md schema and format
Specify the INDEX.md format: required fields, max line limit (~50 lines), room entry structure (name, description, path). This is the palace entry point every agent reads first.
[Read the thread](https://github.com/Nano-Nimbus/locus/issues/1) · 2026-03-02 · closed · 0 comments
The remaining reports are on [the project's issue tracker](https://github.com/Nano-Nimbus/locus/issues).