TaskWing helps me turn a goal into executed tasks with persistent context across AI sessions.
Brand names and logos are trademarks of their respective owners; usage here indicates compatibility, not endorsement.
# 1) Bootstrap project memory
cd your-project
taskwing bootstrap
# 2) Create and activate a plan from one goal
taskwing goal "Add Stripe billing"
# 3) Execute from your AI assistant
/tw-next
# ...work...
/tw-done- Stores architecture decisions, constraints, and patterns in local project memory.
- Generates executable tasks from a goal using that memory.
- Exposes context and task lifecycle tools to AI assistants via MCP.
taskwing bootstraptaskwing goal "<goal>"taskwing tasktaskwing plan statustaskwing slashtaskwing mcptaskwing doctortaskwing configtaskwing start
| Tool | Description |
|---|---|
recall |
Retrieve project knowledge (decisions, patterns, constraints) |
task |
Unified task lifecycle (next, current, start, complete) |
plan |
Plan management (clarify, decompose, expand, generate, finalize, audit) |
code |
Code intelligence (find, search, explain, callers, impact, simplify) |
debug |
Diagnose issues systematically with AI-powered analysis |
remember |
Store knowledge in project memory |
TaskWing supports Bedrock as a first-class provider for chat/planning/query flows.
llm:
provider: bedrock
model: anthropic.claude-sonnet-4-5-20250929-v1:0
bedrock:
region: us-east-1
apiKeys:
bedrock: ${BEDROCK_API_KEY}You can also configure it interactively:
taskwing configRecommended Bedrock model IDs:
anthropic.claude-opus-4-6-v1(highest quality reasoning)anthropic.claude-sonnet-4-5-20250929-v1:0(best default balance)amazon.nova-premier-v1:0(AWS flagship Nova)amazon.nova-pro-v1:0(strong balance)meta.llama4-maverick-17b-instruct-v1:0(open-weight strong general model)
{
"mcpServers": {
"taskwing-mcp": {
"command": "taskwing",
"args": ["mcp"]
}
}
}MIT