fix(memory): setup step 5 check index.json + align docs to real state (#85 )

* fix(memory): check index.json not .rag dir in setup step 5

* docs(readme): align to real state after memory PRs

* chore(env): remove dead vars from env example

* docs(handoff): add handoff + ADR-037 for memory setup step5 fix

* docs(handoff): set PR number

---------

Co-authored-by: opencode-agent <agent@opencode.local>

2026-07-26 20:12:15 +03:00

2.8 KiB

Raw Blame History

opencode-config

Docker-based AI coding assistant with persistent memory — opencode configuration.

Quick start

Docker

git clone https://github.com/slaid098/opencode-config.git
cd opencode-config
cp .env.example .env  # fill in your keys
docker compose up -d

Access at http://localhost:4096.

Bare (without Docker)

git clone https://github.com/slaid098/opencode-config.git
cd opencode-config
opencode  # .opencode/ auto-discovered

Structure

AGENTS.md — global orchestrator rules (main agent = plan only, all via subagents)
.opencode/ — project-local config (auto-discovered, zero env var)
- agents/ — subagent definitions (docs-reviewer, memory-syncer, reviewer)
- commands/ — slash commands (run-pipeline, spec, configure-opencode)
- skills/ — skill definitions (14 skills)
- tools/ — custom tools (commit, create-issue, create-pr, memory-setup, merge-pr, pipeline-status, post-docs-review, post-review, spec-status, tunnel)
- scripts/ — Python scripts (pipeline-status, spec-status, check-adr-refs, etc.)
- opencode.json — main config (providers, MCP servers, permissions)
app_data/workspaces/ — agent working directory
app_data/ssh/ — SSH keys (not in git)
src/ — Python RAG CLI (memory)
docs/ — handoffs, decisions (ADRs), project map
.github/workflows/ — CI workflows (ubuntu-latest)

Configuration

Copy .env.example to .env and fill in:

Variable	Description
`AI_PROVIDER_BASE_URL`	AI provider API URL
`AI_PROVIDER_API_KEY`	AI provider API key
`OPENAI_BASE_URL`	Embeddings API URL (OpenRouter default)
`OPENAI_API_KEY`	Embeddings API key (OpenRouter)
`OPENAI_EMBEDDING_MODEL`	Embedding model (default: `qwen/qwen3-embedding-8b`)
`OPENAI_EMBEDDING_BATCH_SIZE`	Embedding batch size (default: 50)
`OPENCODE_SERVER_PASSWORD`	opencode server password
`GITHUB_TOKEN`	GitHub personal access token
`CONTEXT7_API_KEY`	Context7 MCP API key
`OPENCODE_MEMORY_REMOTE`	Git remote for your opencode-memory fork (required)
`MEMORY_CHUNK_SIZE`	Memory index chunk size (default: 512)
`MEMORY_CHUNK_OVERLAP`	Memory index chunk overlap (default: 64)
`ANTIDETECT_BROWSER_MCP_URL`	Antidetect browser MCP URL (optional)

Memory setup

Memory uses @mathew-cf/opencode-memory plugin (hybrid search: ripgrep + cloud embeddings (OpenRouter Qwen3 8B)).

OPENCODE_MEMORY_DIR env var points to memory directory (default: /root/.local/share/opencode/opencode-memory)
OPENCODE_MEMORY_REMOTE must point at your git remote — fork the upstream slaid098/opencode-memory repo and set the URL in .env
Run .opencode/scripts/setup-memory.sh to initialize memory repo

License

MIT — see LICENSE

2.8 KiB Raw Blame History