All plugins are stdlib-only Python with no external dependencies.
- auto-summarizer: extractive conversation summary for long context
compression, persists per-agent summaries to disk
- conversation-logger: JSONL audit logs per agent with ISO 8601
timestamps, auto-creates log directory tree
- guardrails: safety filter detecting PII (email, phone, SSN, CC),
prompt injection patterns, and credential exposure via regex
- keyword-memory: extracts entities (emails, URLs, dates, technical
terms like camelCase/snake_case/dotted identifiers) as memories
- sentiment-tracker: keyword-based sentiment scoring with intensifiers
and negation handling, only injects context for non-neutral sentiment
- todo-tracker: detects action items via 7 task patterns, tracks
completion, deduplicates, persists per-agent with 20-item FIFO limit
33 agent READMEs, 14 hand READMEs, 2 plugin READMEs
(echo-memory + hooks), and 2 skill READMEs
(custom-skill-prompt + custom-skill-python).
Each README documents the component's purpose, configuration,
and usage based on its TOML definition.
Each directory (agents, hands, integrations, plugins, providers,
scripts, skills) now has a README documenting its TOML format,
current contents, and contribution steps.
- Add Doubao Seed 2.0 Pro (frontier, 256K context, 128K output)
- Add Doubao Seed 2.0 Code
- Add Doubao Seed 1.8 (multimodal agent model with vision)
- Add Doubao Seed 1.6 Vision
- Update existing 2.0 Lite/Mini with correct specs (256K/128K, vision)
- Update global alias "doubao" to point to 2.0 Pro
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add openrouter/stepfun/step-3.5-flash:free — a free model with 128K
context, tool support, and streaming. Used as default for one-click
cloud deployments.
Community-maintained TOML catalog for LibreFang. New models can be added
via PR without requiring a LibreFang binary release.
Includes validation script, bilingual docs, and GitHub templates.
Evan Hu