Twiceshy

app.twiceshyPublished by twiceshy.appOfficial publisherv0.1.0Updated Oct 24, 2026

Experience memory for coding agents: validated traps, fixes and dead-ends at decision time.

VerifiedStreamable HTTPWeb executableKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Twiceshy is a hosted experience-memory service that feeds validated engineering traps, fixes and dead-ends to coding agents at decision time.

What you can do
  • Retrieve relevant experience records for a coding task, filtered by stack fingerprint and a relevance floor so weak matches return nothing.
  • Pull records over MCP tools on a streamable HTTP endpoint, alongside push delivery of trap cards through Claude Code hooks.
  • Work from git-backed markdown records with provenance, indexed by BM25 plus dense vectors.
  • Propose new records, which are quarantined and promoted only after sandbox validation and human review.
When to use it
Useful when a coding agent keeps repeating known mistakes and you want it to see prior issues, root causes and validated fixes before choosing an approach. Best suited to teams willing to maintain a shared, reviewed corpus of engineering experience.
Requirements
A remote MCP endpoint at api.twiceshy.app over streamable HTTP. A bearer token in the Authorization header, obtained from the self-serve alpha signup; no local runtime or environment variables are declared.
Before you install
The Authorization bearer token is a secret and must be kept private. The service is a hosted alpha, so availability and behavior may change. Agent-proposed records are quarantined and require human PR review before promotion, and external contributions need a signed CLA.

Installation

In SourceWeft

  1. Open Twiceshy in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/app.twiceshy%2Ftwiceshy/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "twiceshy": {
      "type": "http",
      "url": "https://api.twiceshy.app/",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

twiceshy

Once bitten, twice shy.

A self-hosted service that feeds hard-won engineering experience — issues, dead-ends, root causes, validated fixes — to LLM coding agents at decision time, so they stop repeating known mistakes on autopilot. Records are git-backed and provenance-aware; automatic retrieval applies a relevance floor so a weak match can return nothing.

Hosted alpha

The hosted instance runs at twiceshy.app — self-serve tokens, remote MCP endpoint https://api.twiceshy.app/. External contributions require a signed CLA before merge (ADR-0002).

How it works (the locked architecture)

  • Source of truth: git-backed markdown experience records (YAML frontmatter
    • narrative) — format in docs/SCHEMA.md. The corpus is a separate versioned data product (twiceshy-corpus, ADR-0021); the engine ships a small frozen fixture (internal/testcorpus/) for tests.
  • Index: one derived, always-rebuildable SQLite file (FTS5 plus cached, pure-Go dense vectors for pull retrieval).
  • Retrieval: fingerprint-exact → BM25 → dense (RRF), stack-fingerprint filtered, hard cap k≤3 with a relevance floor — below it, nothing is injected.
  • Channels: push (Claude Code hooks → trap cards), pull (MCP tools over streamable HTTP), index (generated one-liners).
  • Trust: agent-proposed records are quarantined; promotion = sandbox fail-to-pass validation + human PR review. A new record IS a pull request.
  • Doctors: background jobs that dedup, staleness-check, re-execute repros (CI for memories), decay, and abstract.

Full rationale: docs/research/EXPERIENCE_SERVICE_RESEARCH.md and docs/adr/ADR-0001-architecture.md.

Status

The core service is available as a hosted alpha. For the canonical snapshot of what ships now and the current roadmap, see docs/NEXT_FEATURES.md; deployment and operating details live in docs/DEPLOY-public-alpha.md.

Development

sh
make ci    # lint + race tests + coverage floor — what CI runs

See docs/CONVENTIONS.md and docs/CONTEXT.md first.

License

AGPL-3.0-only. Contribution and corpus licensing: docs/adr/ADR-0002-licensing-strategy.md.

Source: README.md at commit aa8f1d8

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

60% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts