The community has provided a number of addtional implementations, see the `Tendermint Ecosystem` in [the documentation](http://tendermint.readthedocs.io/en/master/).
We provide three implementations of the ABCI in Go:
- ABCI-socket
- GRPC
- Golang in-process
### Socket
ABCI is best implemented as a streaming protocol.
The socket implementation provides for asynchronous, ordered message passing over unix or tcp.
Messages are serialized using Protobuf3 and length-prefixed.
Protobuf3 doesn't have an official length-prefix standard, so we use our own. The first byte represents the length of the big-endian encoded length.
For example, if the Protobuf3 encoded ABCI message is `0xDEADBEEF` (4 bytes), the length-prefixed message is `0x0104DEADBEEF`. If the Protobuf3 encoded ABCI message is 65535 bytes long, the length-prefixed message would be like `0x02FFFF...`.
### GRPC
GRPC is an rpc framework native to Protocol Buffers with support in many languages.
Implementing the ABCI using GRPC can allow for faster prototyping, but is expected to be much slower than
the ordered, asynchronous socket protocol.
Note the length-prefixing used in the socket implementation does not apply for GRPC.
### In Process
The simplest implementation just uses function calls within Go.
This means ABCI applications written in Golang can be compiled with TendermintCore and run as a single binary.
## Example Apps
The `abci-cli` tool wraps any ABCI client and can be used for probing/testing an ABCI application.
See [the documentation](http://tendermint.readthedocs.io/en/master/) for more details.
Multiple example apps are included:
- the `counter` application, which illustrates nonce checking in txs
- the `dummy` application, which illustrates a simple key-value merkle tree
- the `dummy --persistent` application, which augments the dummy with persistence and validator set changes
ABCI requests/responses are defined as simple Protobuf messages in [this schema file](https://github.com/tendermint/abci/blob/master/types/types.proto).
TendermintCore sends the requests, and the ABCI application sends the responses.
Here, we describe the requests and responses as function arguments and return values, and make some notes about usage:
CheckTx can happen interspersed with DeliverTx, but they happen on different ABCI connections - CheckTx from the mempool connection, and DeliverTx from the consensus connection. During Commit, the mempool is locked, so you can reset the mempool state to the latest state after running all those DeliverTxs, and then the mempool will re-run whatever txs it has against that latest mempool state.
*`Height (uint64)`: The block height for which you want the query (default=0 returns data for the latest committed block). Note that this is the height of the block containing the application's Merkle root hash, which represents the state as it was after committing the block at Height-1
*`Height (uint64)`: The block height from which data was derived. Note that this is the height of the block containing the application's Merkle root hash, which represents the state as it was after committing the block at Height-1
*Please note* The current implementation of go-merkle doesn't support querying proofs from past blocks, so for the present moment, any height other than 0 will return an error (recall height=0 defaults to latest block). Hopefully this will be improved soon(ish)
* Echo a string to test an abci client/server implementation
#### Flush
* __Usage__:<br/>
* Signals that messages queued on the client should be flushed to the server. It is called periodically by the client implementation to ensure asynchronous requests are actually sent, and is called immediately to make a synchronous request, which returns when the Flush response comes back.
